fatescript / centernet-better Goto Github PK

View Code? Open in Web Editor NEW

548.0 548.0 104.0 190 KB

An easy to understand and better performance version of CenterNet

License: Apache License 2.0

Python 81.20% C++ 4.46% Cuda 14.34%

computer-vision deep-learning object-detection

centernet-better's People

Contributors

Stargazers

Watchers

Forkers

robot-ai-machinelearning wmpscc eeking hajungong007 lliai forks-learning chaoshengt sdzzlover mjanddy penghaozhou zechendev wyjforwjy felixzhang7 crazyvertigo lbin icucu wuxiaolianggit peizesun jackweiwang liufeng1990 xingyizhou zyg11 hailuo0112 ffudi dicksonyuan sunlerzry happog tjusym renguanglei96 mikangel guanghan zhanqiqi simon821 daonancai karim-ahmed yangkang779 quark30 powerxiaobei mwl5 xgmiao hongweixie harrylin-hyl sailyung chaomath lijuny tdtce limitmhw wj1214 lxngoddess5321 archizx hiyyg zhjpqq adrianosantospb skaldesh hnqin-xdu snowsil xd-liu lih627 ikramullahniazi cv-ip progressforever xrosliang zivkidd funkykoki flyinggh lijianshe02 barangursoy avatar196kc handsomeyss wang-qinyu 1364468984qqcom wharu philistine123 hoangxtr mox233 youonlytrackonce anshkumar senwang98 95hali74 yanshuang17 collector-m hakanardo jiangzqyw raxxu timothylimyl javalier taikangsheng nialthrov sunshine411 wxd000000 lufanma psandovalsegura johnqczhang oddeirikigland than-duc-huy yueliao shilu90 haustcvpr2020 dickymuhr anycle

centernet-better's Issues

how's your model converge ?

From my experiments on single GPU the model impossible to converge.

I have changed learing from 0.02 to 0.01, also 0.0025, if I keep 0.02 the loss will became Nan quickly, I assume you using 0.02 for 8 GPUs defaultly.

My question is that, in whatever minimal learing rate the model impossible to cnverge on single GPU. After 9999 iterations the model loss still very high and the loss like this:

 iter: 9999  total_loss: 6.486  loss_cls: 4.432  loss_box_wh: 1.896  loss_center_reg: 0.260  tim: 0.7158  data_tim: 0.2920  lr: 0.007393  mem: 5030M

How's your learning curve on 8 GPUs? What's the loss going to be?

Could you please provide the link for pretrained model of res50?

Thank you for your great work.
As what has been mentioned in the repo, the centernet is really hard to converge.
And I also read your closed issues , seems that you are using torchvision pretrained models. But when I tried to load the torchvision pretrained r50 model, the weights can't be loaded, the same as detectron2.
If it's possible, please provide the link of res50 pretrained model. Thanks a lot.
And also for people who are struggling from the converge problem, lower down the lr may not be much helpful.

是否实现了论文中的kitti 3D检测部分？如果实现的话改动是不是很大呢？

win10

Hi! Thank you for publishing this code.But can l run the code on Windos10?

error in modulated_deformable_col2im_coord_cuda: invalid device function

Hello, could you help me?
I am running the code with the following problem:

error in modulated_deformable_col2im_coord_cuda: invalid device function
error in modulated_deformable_col2im_cuda: invalid device function
error in modulated_deformable_im2col_cuda: invalid device function

Environmental information that the program prints:

sys.platform linux
Python 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
Numpy 1.19.4
dl_lib Compiler GCC 5.4
dl_lib CUDA Compiler 10.0
dl_lib_ENV_MODULE
PyTorch 1.4.0+cu100
PyTorch Debug Build False
torchvision 0.5.0+cu100
CUDA available True
GPU 0,1,2,3,4,5,6,7 GeForce RTX 2080 Ti
CUDA_HOME /usr/local/cuda
NVCC Cuda compilation tools, release 10.0, V10.0.130
Pillow 8.0.1
cv2 4.4.0

PyTorch built with:

GCC 7.3
Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CUDA Runtime 10.0
NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
CuDNN 7.6.3
Magma 2.5.1
Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

some module missing in benchmark.py

No module named 'dl_lib.config'

gcc error？

I try to gcc4.9.3/5.5/7.0, but all of them cannot building. Can you give me a hand?
Thank you very much!
cuda 10.1, torch1.4

cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
/home/cc631/code/Dilated-FPN/CenterNet-better/dl_lib/layers/vision.cpp:4:10: fatal error: cuda_runtime_api.h:
#include <cuda_runtime_api.h>
^~~~~~~~~~~~~~~~~~~~
compilation terminated.
error: command 'gcc' failed with exit status 1
----------------------------------------
ERROR: Command errored out with exit status 1: /home/cc631/anaconda3/envs/pytorch1.4/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/cc631/hailong/code/Dilated-FPN/CenterNet-better/setup.py'"'"'; file='"'"'/home/cc631/hailong/code/Dilated-FPN/CenterNet-better/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.

ModuleNotFoundError: No module named 'config'

Traceback (most recent call last):
File "/home/wangqinyu/STR/CenterNet-better/tools/test_net.py", line 27, in
from config import config
ModuleNotFoundError: No module named 'config'

cannot import name 'config' from 'config'

when i run the file train_net.py, I met the error :
cannot import name 'config' from 'config'.
How can I solve it?

How to train custom dataset about this model?

How to set the path and config when i want to train the model through a custom dataset changed to detectron2 format ??

Thank you for this repo!!!

I am trying to understand details of centrenet these days,
thank you so much for writing this repo!!!

about set batch size

I have not enough GPUs and can only use 16 batchsize.
how to set BASE_LR and MAX_ITER config in 16 batchsize

what net inside tools/test_net.py?

test_net.py

CenterNet-better/tools/test_net.py

Line 27 in 7336530

from config import config

CenterNet-better/tools/test_net.py

Line 34 in 7336530

from net import build_model

are u sure these line can be imported? from where?

[Documentation Request] performance gains

Hi, thanks for this repo. If you would, could you explain what implementation details you attribute the performance gains you've measure to?

I train from the pretain model res101, but the result doesn't work

How to solve this red error when using PyCharm

Hi, guys,
I am learning this repo and using PyCharm.
But I meet a problem that there is a red error when checking the code in PyCharm, although the code seems to run normally.
It shows like this,

Could please tell me how to fix this?

Your answer and idea will be appreciated!

no modules

Hi, thank you for your great work, but i have some questions:
(1)from config import config where is the "config" module？
(2)from net import build_model where is the "net" module?
Could you share the modules with me? Thank you very much!

hi, can you tell me how to train my own custom dataset

can you tell me how to train my own custom dataset

What is the meaning of "gaussian_iou" in the dataset?

Hi, guys,
I am learning about CenterNet these days, and I want to know what is the meaning of gaussian_iou = 0.7 for the dataset?

Any idea or answer will be appreciated!

Boxes elimination may be omitted

Hi, thx for your work.

Diving into the code, I notice that during inference the detector always predicts 100 (set with topK hyper-parameter) instances per image. For the whole COCO validation dataset (5000 images), 500000 instances are saved into coco_instances_results.json and instances_predictions.pth.

Thus, I doubt that some post-process steps may be omitted. If I misunderstood, I will be appreciated if you could solve my confusion. Thx.

What should i do to solve this ERROR?

Installing collected packages: termcolor, tabulate, Shapely, absl-py, markdown, grpcio, oauthlib, requests-oauthlib, google-auth-oauthlib, tensorboard-plugin-wit, tensorboard, portalocker, dl-lib
Running setup.py develop for dl-lib
ERROR: Command errored out with exit status 1:
command: /home/noob/anaconda3/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/noob/projects/PycharmProjects/CenterNet-better-master/setup.py'"'"'; file='"'"'/home/noob/projects/PycharmProjects/CenterNet-better-master/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps
cwd: /home/noob/projects/PycharmProjects/CenterNet-better-master/
Complete output (1921 lines):
running develop
running egg_info
writing dl_lib.egg-info/PKG-INFO
writing dependency_links to dl_lib.egg-info/dependency_links.txt
writing requirements to dl_lib.egg-info/requires.txt
writing top-level names to dl_lib.egg-info/top_level.txt
reading manifest file 'dl_lib.egg-info/SOURCES.txt'
writing manifest file 'dl_lib.egg-info/SOURCES.txt'
running build_ext
building 'dl_lib.C' extension
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign
creating /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable
Emitting ninja build file /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/5] /usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda_kernel.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
FAILED: /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda_kernel.o
/usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda_kernel.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
/usr/include/stdint.h(43): error: identifier "__int_least8_t" is undefined

/usr/include/stdint.h(44): error: identifier "__int_least16_t" is undefined

/usr/include/stdint.h(45): error: identifier "__int_least32_t" is undefined

/usr/include/stdint.h(46): error: identifier "__int_least64_t" is undefined

/usr/include/stdint.h(49): error: identifier "__uint_least8_t" is undefined

/usr/include/stdint.h(50): error: identifier "__uint_least16_t" is undefined

/usr/include/stdint.h(51): error: identifier "__uint_least32_t" is undefined

/usr/include/stdint.h(52): error: identifier "__uint_least64_t" is undefined

/usr/include/c++/7/cstdint(77): error: "uint_least16_t" has already been declared in the current scope

/usr/include/c++/7/cstdint(78): error: "uint_least32_t" has already been declared in the current scope

10 errors detected in the compilation of "/tmp/tmpxft_00006e16_00000000-6_deform_conv_cuda_kernel.cpp1.ii".
[2/5] /usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cuda.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
FAILED: /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cuda.o
/usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cuda.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
/usr/include/stdint.h(43): error: identifier "__int_least8_t" is undefined

/usr/include/stdint.h(44): error: identifier "__int_least16_t" is undefined

/usr/include/stdint.h(45): error: identifier "__int_least32_t" is undefined

/usr/include/stdint.h(46): error: identifier "__int_least64_t" is undefined

/usr/include/stdint.h(49): error: identifier "__uint_least8_t" is undefined

/usr/include/stdint.h(50): error: identifier "__uint_least16_t" is undefined

/usr/include/stdint.h(51): error: identifier "__uint_least32_t" is undefined

/usr/include/stdint.h(52): error: identifier "__uint_least64_t" is undefined

/usr/include/c++/7/cstdint(77): error: "uint_least16_t" has already been declared in the current scope

/usr/include/c++/7/cstdint(78): error: "uint_least32_t" has already been declared in the current scope

10 errors detected in the compilation of "/tmp/tmpxft_00006e15_00000000-6_ROIAlign_cuda.cpp1.ii".
[3/5] c++ -MMD -MF /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.o.d -pthread -B /home/noob/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
FAILED: /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.o
c++ -MMD -MF /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.o.d -pthread -B /home/noob/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/stdint.h:9:0,
                 from /usr/include/c++/7/cstdint:41,
                 from /usr/include/c++/7/bits/char_traits.h:501,
                 from /usr/include/c++/7/ios:40,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdint.h:43:9: error: ‘__int_least8_t’ does not name a type; did you mean ‘__intptr_t’?
 typedef __int_least8_t int_least8_t;
         ^~~~~~~~~~~~~~
         __intptr_t
/usr/include/stdint.h:44:9: error: ‘__int_least16_t’ does not name a type; did you mean ‘__int16_t’?
 typedef __int_least16_t int_least16_t;
         ^~~~~~~~~~~~~~~
         __int16_t
/usr/include/stdint.h:45:9: error: ‘__int_least32_t’ does not name a type; did you mean ‘__int32_t’?
 typedef __int_least32_t int_least32_t;
         ^~~~~~~~~~~~~~~
         __int32_t
/usr/include/stdint.h:46:9: error: ‘__int_least64_t’ does not name a type; did you mean ‘__int64_t’?
 typedef __int_least64_t int_least64_t;
         ^~~~~~~~~~~~~~~
         __int64_t
/usr/include/stdint.h:49:9: error: ‘__uint_least8_t’ does not name a type; did you mean ‘__uintmax_t’?
 typedef __uint_least8_t uint_least8_t;
         ^~~~~~~~~~~~~~~
         __uintmax_t
/usr/include/stdint.h:50:9: error: ‘__uint_least16_t’ does not name a type; did you mean ‘__uint16_t’?
 typedef __uint_least16_t uint_least16_t;
         ^~~~~~~~~~~~~~~~
         __uint16_t
/usr/include/stdint.h:51:9: error: ‘__uint_least32_t’ does not name a type; did you mean ‘__uint32_t’?
 typedef __uint_least32_t uint_least32_t;
         ^~~~~~~~~~~~~~~~
         __uint32_t
/usr/include/stdint.h:52:9: error: ‘__uint_least64_t’ does not name a type; did you mean ‘__uint64_t’?
 typedef __uint_least64_t uint_least64_t;
         ^~~~~~~~~~~~~~~~
         __uint64_t
In file included from /usr/include/c++/7/bits/char_traits.h:501:0,
                 from /usr/include/c++/7/ios:40,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/c++/7/cstdint:58:11: error: ‘::int_least8_t’ has not been declared
   using ::int_least8_t;
           ^~~~~~~~~~~~
/usr/include/c++/7/cstdint:59:11: error: ‘::int_least16_t’ has not been declared
   using ::int_least16_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:60:11: error: ‘::int_least32_t’ has not been declared
   using ::int_least32_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:61:11: error: ‘::int_least64_t’ has not been declared
   using ::int_least64_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:76:11: error: ‘::uint_least8_t’ has not been declared
   using ::uint_least8_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:77:11: error: ‘::uint_least16_t’ has not been declared
   using ::uint_least16_t;
           ^~~~~~~~~~~~~~
/usr/include/c++/7/cstdint:78:11: error: ‘::uint_least32_t’ has not been declared
   using ::uint_least32_t;
           ^~~~~~~~~~~~~~
/usr/include/c++/7/cstdint:79:11: error: ‘::uint_least64_t’ has not been declared
   using ::uint_least64_t;
           ^~~~~~~~~~~~~~
In file included from /usr/include/stdio.h:870:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getchar()’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:46:10: error: ‘_IO_getc’ was not declared in this scope
   return _IO_getc (stdin);
          ^~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:46:10: note: suggested alternative: ‘ungetc’
   return _IO_getc (stdin);
          ^~~~~~~~
          ungetc
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int fgetc_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:55:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:55:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getc_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:65:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:65:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getchar_unlocked()’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:72:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (stdin);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:72:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (stdin);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putchar(int)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:81:10: error: ‘_IO_putc’ was not declared in this scope
   return _IO_putc (__c, stdout);
          ^~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:81:10: note: suggested alternative: ‘_ISpunct’
   return _IO_putc (__c, stdout);
          ^~~~~~~~
          _ISpunct
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int fputc_unlocked(int, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:90:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:90:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putc_unlocked(int, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:100:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:100:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putchar_unlocked(int)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:107:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, stdout);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:107:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, stdout);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio.h:114:16: error: ‘_IO_ssize_t’ does not name a type; did you mean ‘__ssize_t’?
 __STDIO_INLINE _IO_ssize_t
                ^~~~~~~~~~~
                __ssize_t
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int feof_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:127:10: error: ‘_IO_feof_unlocked’ was not declared in this scope
   return _IO_feof_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:127:10: note: suggested alternative: ‘feof_unlocked’
   return _IO_feof_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~
          feof_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int ferror_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:134:10: error: ‘_IO_ferror_unlocked’ was not declared in this scope
   return _IO_ferror_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:134:10: note: suggested alternative: ‘ferror_unlocked’
   return _IO_ferror_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~~~
          ferror_unlocked
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:27:7: error: ‘_G_va_list’ has not been declared
       _G_va_list __ap) __THROW;
       ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/os_defines.h:39,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/c++config.h:533,
                 from /usr/include/c++/7/iosfwd:38,
                 from /usr/include/c++/7/ios:38,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:43:1: error: ‘_G_va_list’ has not been declared
 __NTH (vsprintf (char *__restrict __s, const char *__restrict __fmt,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vsprintf(char*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:43:1: error: conflicting declaration of C function ‘int vsprintf(char*, const char*, int)’
 __NTH (vsprintf (char *__restrict __s, const char *__restrict __fmt,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:349:12: note: previous declaration ‘int vsprintf(char*, const char*, __va_list_tag*)’
 extern int vsprintf (char *__restrict __s, const char *__restrict __format,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:47:32: error: invalid conversion from ‘int’ to ‘__va_list_tag*’ [-fpermissive]
        __bos (__s), __fmt, __ap);
                                ^
<built-in>: note:   initializing argument 5 of ‘int __builtin___vsprintf_chk(char*, int, long unsigned int, const char*, __va_list_tag*)’
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:57:8: error: ‘_G_va_list’ has not been declared
        _G_va_list __ap) __THROW;
        ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/os_defines.h:39,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/c++config.h:533,
                 from /usr/include/c++/7/iosfwd:38,
                 from /usr/include/c++/7/ios:38,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:74:1: error: ‘_G_va_list’ has not been declared
 __NTH (vsnprintf (char *__restrict __s, size_t __n,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vsnprintf(char*, size_t, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:74:1: error: conflicting declaration of C function ‘int vsnprintf(char*, size_t, const char*, int)’
 __NTH (vsnprintf (char *__restrict __s, size_t __n,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:358:12: note: previous declaration ‘int vsnprintf(char*, size_t, const char*, __va_list_tag*)’
 extern int vsnprintf (char *__restrict __s, size_t __maxlen,
            ^~~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:78:33: error: invalid conversion from ‘int’ to ‘__va_list_tag*’ [-fpermissive]
         __bos (__s), __fmt, __ap);
                                 ^
<built-in>: note:   initializing argument 6 of ‘int __builtin___vsnprintf_chk(char*, long unsigned int, int, long unsigned int, const char*, __va_list_tag*)’
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:89:40: error: ‘_G_va_list’ has not been declared
       const char *__restrict __format, _G_va_list __ap);
                                        ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:91:6: error: ‘_G_va_list’ has not been declared
      _G_va_list __ap);
      ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:114:40: error: ‘_G_va_list’ has not been declared
 vprintf (const char *__restrict __fmt, _G_va_list __ap)
                                        ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vprintf(const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:114:1: error: conflicting declaration of C function ‘int vprintf(const char*, int)’
 vprintf (const char *__restrict __fmt, _G_va_list __ap)
 ^~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:347:12: note: previous declaration ‘int vprintf(const char*, __va_list_tag*)’
 extern int vprintf (const char *__restrict __format, __gnuc_va_list __arg);
            ^~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:125:34: error: ‘_G_va_list’ has not been declared
    const char *__restrict __fmt, _G_va_list __ap)
                                  ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vfprintf(FILE*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:124:1: error: conflicting declaration of C function ‘int vfprintf(FILE*, const char*, int)’
 vfprintf (FILE *__restrict __stream,
 ^~~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:341:12: note: previous declaration ‘int vfprintf(FILE*, const char*, __va_list_tag*)’
 extern int vfprintf (FILE *__restrict __s, const char *__restrict __format,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:134:37: error: ‘_G_va_list’ has not been declared
       const char *__restrict __fmt, _G_va_list __arg)
                                     ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:150:51: error: ‘_G_va_list’ has not been declared
 vdprintf (int __fd, const char *__restrict __fmt, _G_va_list __ap)
                                                   ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vdprintf(int, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:150:1: error: conflicting declaration of C function ‘int vdprintf(int, const char*, int)’
 vdprintf (int __fd, const char *__restrict __fmt, _G_va_list __ap)
 ^~~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:379:12: note: previous declaration ‘int vdprintf(int, const char*, __va_list_tag*)’
 extern int vdprintf (int __fd, const char *__restrict __fmt,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:162:38: error: ‘_G_va_list’ has not been declared
        const char *__restrict __fmt, _G_va_list __arg)
                                      ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:171:7: error: ‘_G_va_list’ has not been declared
       _G_va_list __args)
       ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/os_defines.h:39,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/c++config.h:533,
                 from /usr/include/c++/7/iosfwd:38,
                 from /usr/include/c++/7/ios:38,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:207:1: error: ‘_G_va_list’ has not been declared
 __NTH (vasprintf (char **__restrict __ptr, const char *__restrict __fmt,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vasprintf(char**, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:207:1: error: conflicting declaration of C function ‘int vasprintf(char**, const char*, int)’
 __NTH (vasprintf (char **__restrict __ptr, const char *__restrict __fmt,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:366:12: note: previous declaration ‘int vasprintf(char**, const char*, __va_list_tag*)’
 extern int vasprintf (char **__restrict __ptr, const char *__restrict __f,
            ^~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/os_defines.h:39,
                 from /usr/include/x86_64-linux-gnu/c++/7/bits/c++config.h:533,
                 from /usr/include/c++/7/iosfwd:38,
                 from /usr/include/c++/7/ios:38,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:214:1: error: ‘_G_va_list’ has not been declared
 __NTH (obstack_vprintf (struct obstack *__restrict __obstack,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int obstack_vprintf(obstack*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:214:1: error: conflicting declaration of C function ‘int obstack_vprintf(obstack*, const char*, int)’
 __NTH (obstack_vprintf (struct obstack *__restrict __obstack,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/stdio.h:835:12: note: previous declaration ‘int obstack_vprintf(obstack*, const char*, __va_list_tag*)’
 extern int obstack_vprintf (struct obstack *__restrict __obstack,
            ^~~~~~~~~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/bits/locale_classes.h:40,
                 from /usr/include/c++/7/bits/ios_base.h:41,
                 from /usr/include/c++/7/ios:42,
                 from /usr/include/c++/7/istream:38,
                 from /usr/include/c++/7/sstream:38,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:147,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘size_t fread_unlocked(void*, size_t, size_t, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:371:14: error: ‘_IO_getc_unlocked’ was not declared in this scope
    int __c = _IO_getc_unlocked (__stream);
              ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:371:14: note: suggested alternative: ‘fgetc_unlocked’
    int __c = _IO_getc_unlocked (__stream);
              ^~~~~~~~~~~~~~~~~
              fgetc_unlocked
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/typeid.h:3:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:7,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:9,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:7,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/usr/include/c++/7/atomic: At global scope:
/usr/include/c++/7/atomic:942:18: error: ‘int_least8_t’ was not declared in this scope
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                  ^~~~~~~~~~~~
/usr/include/c++/7/atomic:942:18: note: suggested alternative: ‘int_fast8_t’
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                  ^~~~~~~~~~~~
                  int_fast8_t
/usr/include/c++/7/atomic:942:30: error: template argument 1 is invalid
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                              ^
/usr/include/c++/7/atomic:945:18: error: ‘uint_least8_t’ was not declared in this scope
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:945:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                  ^~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:945:31: error: template argument 1 is invalid
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                               ^
/usr/include/c++/7/atomic:948:18: error: ‘int_least16_t’ was not declared in this scope
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:948:18: note: suggested alternative: ‘uint_least16_t’
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                  ^~~~~~~~~~~~~
                  uint_least16_t
/usr/include/c++/7/atomic:948:31: error: template argument 1 is invalid
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                               ^
/usr/include/c++/7/atomic:954:18: error: ‘int_least32_t’ was not declared in this scope
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:954:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                  ^~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:954:31: error: template argument 1 is invalid
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                               ^
/usr/include/c++/7/atomic:960:18: error: ‘int_least64_t’ was not declared in this scope
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:960:18: note: suggested alternative: ‘int_fast64_t’
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                  ^~~~~~~~~~~~~
                  int_fast64_t
/usr/include/c++/7/atomic:960:31: error: template argument 1 is invalid
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                               ^
/usr/include/c++/7/atomic:963:18: error: ‘uint_least64_t’ was not declared in this scope
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                  ^~~~~~~~~~~~~~
/usr/include/c++/7/atomic:963:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                  ^~~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:963:32: error: template argument 1 is invalid
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                                ^
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:3:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h: In function ‘at::Tensor dl_lib::ROIAlign_forward(const at::Tensor&, const at::Tensor&, float, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h:62:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (input.type().is_cuda()) {
                  ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:3:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h: In function ‘at::Tensor dl_lib::ROIAlign_backward(const at::Tensor&, const at::Tensor&, float, int, int, int, int, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h:98:17: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (grad.type().is_cuda()) {
                 ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/TensorUtils.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp:2:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
[4/5] /usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
FAILED: /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda.o
/usr/local/cuda-10.2/bin/nvcc -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda.cu -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
/usr/include/stdint.h(43): error: identifier "__int_least8_t" is undefined

/usr/include/stdint.h(44): error: identifier "__int_least16_t" is undefined

/usr/include/stdint.h(45): error: identifier "__int_least32_t" is undefined

/usr/include/stdint.h(46): error: identifier "__int_least64_t" is undefined

/usr/include/stdint.h(49): error: identifier "__uint_least8_t" is undefined

/usr/include/stdint.h(50): error: identifier "__uint_least16_t" is undefined

/usr/include/stdint.h(51): error: identifier "__uint_least32_t" is undefined

/usr/include/stdint.h(52): error: identifier "__uint_least64_t" is undefined

/usr/include/c++/7/cstdint(77): error: "uint_least16_t" has already been declared in the current scope

/usr/include/c++/7/cstdint(78): error: "uint_least32_t" has already been declared in the current scope

10 errors detected in the compilation of "/tmp/tmpxft_00006e17_00000000-6_deform_conv_cuda.cpp1.ii".
[5/5] c++ -MMD -MF /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.o.d -pthread -B /home/noob/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
FAILED: /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.o
c++ -MMD -MF /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.o.d -pthread -B /home/noob/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/TH -I/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-10.2/include -I/home/noob/anaconda3/include/python3.7m -c -c /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp -o /home/noob/projects/PycharmProjects/CenterNet-better-master/build/temp.linux-x86_64-3.7/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/stdint.h:9:0,
                 from /usr/include/c++/7/cstdint:41,
                 from /usr/include/c++/7/bits/char_traits.h:501,
                 from /usr/include/c++/7/string:40,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdint.h:43:9: error: ‘__int_least8_t’ does not name a type; did you mean ‘__intptr_t’?
 typedef __int_least8_t int_least8_t;
         ^~~~~~~~~~~~~~
         __intptr_t
/usr/include/stdint.h:44:9: error: ‘__int_least16_t’ does not name a type; did you mean ‘__int16_t’?
 typedef __int_least16_t int_least16_t;
         ^~~~~~~~~~~~~~~
         __int16_t
/usr/include/stdint.h:45:9: error: ‘__int_least32_t’ does not name a type; did you mean ‘__int32_t’?
 typedef __int_least32_t int_least32_t;
         ^~~~~~~~~~~~~~~
         __int32_t
/usr/include/stdint.h:46:9: error: ‘__int_least64_t’ does not name a type; did you mean ‘__int64_t’?
 typedef __int_least64_t int_least64_t;
         ^~~~~~~~~~~~~~~
         __int64_t
/usr/include/stdint.h:49:9: error: ‘__uint_least8_t’ does not name a type; did you mean ‘__uintmax_t’?
 typedef __uint_least8_t uint_least8_t;
         ^~~~~~~~~~~~~~~
         __uintmax_t
/usr/include/stdint.h:50:9: error: ‘__uint_least16_t’ does not name a type; did you mean ‘__uint16_t’?
 typedef __uint_least16_t uint_least16_t;
         ^~~~~~~~~~~~~~~~
         __uint16_t
/usr/include/stdint.h:51:9: error: ‘__uint_least32_t’ does not name a type; did you mean ‘__uint32_t’?
 typedef __uint_least32_t uint_least32_t;
         ^~~~~~~~~~~~~~~~
         __uint32_t
/usr/include/stdint.h:52:9: error: ‘__uint_least64_t’ does not name a type; did you mean ‘__uint64_t’?
 typedef __uint_least64_t uint_least64_t;
         ^~~~~~~~~~~~~~~~
         __uint64_t
In file included from /usr/include/c++/7/bits/char_traits.h:501:0,
                 from /usr/include/c++/7/string:40,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/c++/7/cstdint:58:11: error: ‘::int_least8_t’ has not been declared
   using ::int_least8_t;
           ^~~~~~~~~~~~
/usr/include/c++/7/cstdint:59:11: error: ‘::int_least16_t’ has not been declared
   using ::int_least16_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:60:11: error: ‘::int_least32_t’ has not been declared
   using ::int_least32_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:61:11: error: ‘::int_least64_t’ has not been declared
   using ::int_least64_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:76:11: error: ‘::uint_least8_t’ has not been declared
   using ::uint_least8_t;
           ^~~~~~~~~~~~~
/usr/include/c++/7/cstdint:77:11: error: ‘::uint_least16_t’ has not been declared
   using ::uint_least16_t;
           ^~~~~~~~~~~~~~
/usr/include/c++/7/cstdint:78:11: error: ‘::uint_least32_t’ has not been declared
   using ::uint_least32_t;
           ^~~~~~~~~~~~~~
/usr/include/c++/7/cstdint:79:11: error: ‘::uint_least64_t’ has not been declared
   using ::uint_least64_t;
           ^~~~~~~~~~~~~~
In file included from /usr/include/stdio.h:870:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getchar()’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:46:10: error: ‘_IO_getc’ was not declared in this scope
   return _IO_getc (stdin);
          ^~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:46:10: note: suggested alternative: ‘ungetc’
   return _IO_getc (stdin);
          ^~~~~~~~
          ungetc
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int fgetc_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:55:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:55:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getc_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:65:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:65:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (__fp);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int getchar_unlocked()’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:72:10: error: ‘_IO_getc_unlocked’ was not declared in this scope
   return _IO_getc_unlocked (stdin);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:72:10: note: suggested alternative: ‘fgetc_unlocked’
   return _IO_getc_unlocked (stdin);
          ^~~~~~~~~~~~~~~~~
          fgetc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putchar(int)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:81:10: error: ‘_IO_putc’ was not declared in this scope
   return _IO_putc (__c, stdout);
          ^~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:81:10: note: suggested alternative: ‘_ISpunct’
   return _IO_putc (__c, stdout);
          ^~~~~~~~
          _ISpunct
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int fputc_unlocked(int, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:90:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:90:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putc_unlocked(int, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:100:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:100:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, __stream);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int putchar_unlocked(int)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:107:10: error: ‘_IO_putc_unlocked’ was not declared in this scope
   return _IO_putc_unlocked (__c, stdout);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:107:10: note: suggested alternative: ‘putc_unlocked’
   return _IO_putc_unlocked (__c, stdout);
          ^~~~~~~~~~~~~~~~~
          putc_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio.h:114:16: error: ‘_IO_ssize_t’ does not name a type; did you mean ‘__ssize_t’?
 __STDIO_INLINE _IO_ssize_t
                ^~~~~~~~~~~
                __ssize_t
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int feof_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:127:10: error: ‘_IO_feof_unlocked’ was not declared in this scope
   return _IO_feof_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:127:10: note: suggested alternative: ‘feof_unlocked’
   return _IO_feof_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~
          feof_unlocked
/usr/include/x86_64-linux-gnu/bits/stdio.h: In function ‘int ferror_unlocked(FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio.h:134:10: error: ‘_IO_ferror_unlocked’ was not declared in this scope
   return _IO_ferror_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio.h:134:10: note: suggested alternative: ‘ferror_unlocked’
   return _IO_ferror_unlocked (__stream);
          ^~~~~~~~~~~~~~~~~~~
          ferror_unlocked
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:27:7: error: ‘_G_va_list’ has not been declared
       _G_va_list __ap) __THROW;
       ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/bits/libc-header-start.h:33,
                 from /usr/include/limits.h:26,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:194,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/syslimits.h:7,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:34,
                 from /usr/local/cuda-10.2/include/driver_types.h:77,
                 from /usr/local/cuda-10.2/include/builtin_types.h:59,
                 from /usr/local/cuda-10.2/include/cuda_runtime_api.h:139,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:4:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:43:1: error: ‘_G_va_list’ has not been declared
 __NTH (vsprintf (char *__restrict __s, const char *__restrict __fmt,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vsprintf(char*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:43:1: error: conflicting declaration of C function ‘int vsprintf(char*, const char*, int)’
 __NTH (vsprintf (char *__restrict __s, const char *__restrict __fmt,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:349:12: note: previous declaration ‘int vsprintf(char*, const char*, __va_list_tag*)’
 extern int vsprintf (char *__restrict __s, const char *__restrict __format,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:47:32: error: invalid conversion from ‘int’ to ‘__va_list_tag*’ [-fpermissive]
        __bos (__s), __fmt, __ap);
                                ^
<built-in>: note:   initializing argument 5 of ‘int __builtin___vsprintf_chk(char*, int, long unsigned int, const char*, __va_list_tag*)’
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:57:8: error: ‘_G_va_list’ has not been declared
        _G_va_list __ap) __THROW;
        ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/bits/libc-header-start.h:33,
                 from /usr/include/limits.h:26,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:194,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/syslimits.h:7,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:34,
                 from /usr/local/cuda-10.2/include/driver_types.h:77,
                 from /usr/local/cuda-10.2/include/builtin_types.h:59,
                 from /usr/local/cuda-10.2/include/cuda_runtime_api.h:139,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:4:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:74:1: error: ‘_G_va_list’ has not been declared
 __NTH (vsnprintf (char *__restrict __s, size_t __n,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vsnprintf(char*, size_t, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:74:1: error: conflicting declaration of C function ‘int vsnprintf(char*, size_t, const char*, int)’
 __NTH (vsnprintf (char *__restrict __s, size_t __n,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:358:12: note: previous declaration ‘int vsnprintf(char*, size_t, const char*, __va_list_tag*)’
 extern int vsnprintf (char *__restrict __s, size_t __maxlen,
            ^~~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:78:33: error: invalid conversion from ‘int’ to ‘__va_list_tag*’ [-fpermissive]
         __bos (__s), __fmt, __ap);
                                 ^
<built-in>: note:   initializing argument 6 of ‘int __builtin___vsnprintf_chk(char*, long unsigned int, int, long unsigned int, const char*, __va_list_tag*)’
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:89:40: error: ‘_G_va_list’ has not been declared
       const char *__restrict __format, _G_va_list __ap);
                                        ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:91:6: error: ‘_G_va_list’ has not been declared
      _G_va_list __ap);
      ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:114:40: error: ‘_G_va_list’ has not been declared
 vprintf (const char *__restrict __fmt, _G_va_list __ap)
                                        ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vprintf(const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:114:1: error: conflicting declaration of C function ‘int vprintf(const char*, int)’
 vprintf (const char *__restrict __fmt, _G_va_list __ap)
 ^~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:347:12: note: previous declaration ‘int vprintf(const char*, __va_list_tag*)’
 extern int vprintf (const char *__restrict __format, __gnuc_va_list __arg);
            ^~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:125:34: error: ‘_G_va_list’ has not been declared
    const char *__restrict __fmt, _G_va_list __ap)
                                  ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vfprintf(FILE*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:124:1: error: conflicting declaration of C function ‘int vfprintf(FILE*, const char*, int)’
 vfprintf (FILE *__restrict __stream,
 ^~~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:341:12: note: previous declaration ‘int vfprintf(FILE*, const char*, __va_list_tag*)’
 extern int vfprintf (FILE *__restrict __s, const char *__restrict __format,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:134:37: error: ‘_G_va_list’ has not been declared
       const char *__restrict __fmt, _G_va_list __arg)
                                     ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:150:51: error: ‘_G_va_list’ has not been declared
 vdprintf (int __fd, const char *__restrict __fmt, _G_va_list __ap)
                                                   ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vdprintf(int, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:150:1: error: conflicting declaration of C function ‘int vdprintf(int, const char*, int)’
 vdprintf (int __fd, const char *__restrict __fmt, _G_va_list __ap)
 ^~~~~~~~
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:379:12: note: previous declaration ‘int vdprintf(int, const char*, __va_list_tag*)’
 extern int vdprintf (int __fd, const char *__restrict __fmt,
            ^~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:162:38: error: ‘_G_va_list’ has not been declared
        const char *__restrict __fmt, _G_va_list __arg)
                                      ^~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:171:7: error: ‘_G_va_list’ has not been declared
       _G_va_list __args)
       ^~~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/bits/libc-header-start.h:33,
                 from /usr/include/limits.h:26,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:194,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/syslimits.h:7,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:34,
                 from /usr/local/cuda-10.2/include/driver_types.h:77,
                 from /usr/local/cuda-10.2/include/builtin_types.h:59,
                 from /usr/local/cuda-10.2/include/cuda_runtime_api.h:139,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:4:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:207:1: error: ‘_G_va_list’ has not been declared
 __NTH (vasprintf (char **__restrict __ptr, const char *__restrict __fmt,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int vasprintf(char**, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:207:1: error: conflicting declaration of C function ‘int vasprintf(char**, const char*, int)’
 __NTH (vasprintf (char **__restrict __ptr, const char *__restrict __fmt,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:366:12: note: previous declaration ‘int vasprintf(char**, const char*, __va_list_tag*)’
 extern int vasprintf (char **__restrict __ptr, const char *__restrict __f,
            ^~~~~~~~~
In file included from /usr/include/features.h:428:0,
                 from /usr/include/x86_64-linux-gnu/bits/libc-header-start.h:33,
                 from /usr/include/limits.h:26,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:194,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/syslimits.h:7,
                 from /usr/lib/gcc/x86_64-linux-gnu/7/include-fixed/limits.h:34,
                 from /usr/local/cuda-10.2/include/driver_types.h:77,
                 from /usr/local/cuda-10.2/include/builtin_types.h:59,
                 from /usr/local/cuda-10.2/include/cuda_runtime_api.h:139,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:4:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: At global scope:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:214:1: error: ‘_G_va_list’ has not been declared
 __NTH (obstack_vprintf (struct obstack *__restrict __obstack,
 ^
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘int obstack_vprintf(obstack*, const char*, int)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:214:1: error: conflicting declaration of C function ‘int obstack_vprintf(obstack*, const char*, int)’
 __NTH (obstack_vprintf (struct obstack *__restrict __obstack,
 ^
In file included from /usr/include/c++/7/cstdio:42:0,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/stdio.h:835:12: note: previous declaration ‘int obstack_vprintf(obstack*, const char*, __va_list_tag*)’
 extern int obstack_vprintf (struct obstack *__restrict __obstack,
            ^~~~~~~~~~~~~~~
In file included from /usr/include/stdio.h:873:0,
                 from /usr/include/c++/7/cstdio:42,
                 from /usr/include/c++/7/ext/string_conversions.h:43,
                 from /usr/include/c++/7/bits/basic_string.h:6361,
                 from /usr/include/c++/7/string:52,
                 from /usr/include/c++/7/stdexcept:39,
                 from /usr/include/c++/7/array:39,
                 from /usr/include/c++/7/tuple:39,
                 from /usr/include/c++/7/bits/unique_ptr.h:37,
                 from /usr/include/c++/7/memory:80,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/x86_64-linux-gnu/bits/stdio2.h: In function ‘size_t fread_unlocked(void*, size_t, size_t, FILE*)’:
/usr/include/x86_64-linux-gnu/bits/stdio2.h:371:14: error: ‘_IO_getc_unlocked’ was not declared in this scope
    int __c = _IO_getc_unlocked (__stream);
              ^~~~~~~~~~~~~~~~~
/usr/include/x86_64-linux-gnu/bits/stdio2.h:371:14: note: suggested alternative: ‘fgetc_unlocked’
    int __c = _IO_getc_unlocked (__stream);
              ^~~~~~~~~~~~~~~~~
              fgetc_unlocked
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/typeid.h:3:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:7,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:9,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:7,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/usr/include/c++/7/atomic: At global scope:
/usr/include/c++/7/atomic:942:18: error: ‘int_least8_t’ was not declared in this scope
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                  ^~~~~~~~~~~~
/usr/include/c++/7/atomic:942:18: note: suggested alternative: ‘int_fast8_t’
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                  ^~~~~~~~~~~~
                  int_fast8_t
/usr/include/c++/7/atomic:942:30: error: template argument 1 is invalid
   typedef atomic<int_least8_t>  atomic_int_least8_t;
                              ^
/usr/include/c++/7/atomic:945:18: error: ‘uint_least8_t’ was not declared in this scope
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:945:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                  ^~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:945:31: error: template argument 1 is invalid
   typedef atomic<uint_least8_t>  atomic_uint_least8_t;
                               ^
/usr/include/c++/7/atomic:948:18: error: ‘int_least16_t’ was not declared in this scope
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:948:18: note: suggested alternative: ‘uint_least16_t’
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                  ^~~~~~~~~~~~~
                  uint_least16_t
/usr/include/c++/7/atomic:948:31: error: template argument 1 is invalid
   typedef atomic<int_least16_t>  atomic_int_least16_t;
                               ^
/usr/include/c++/7/atomic:954:18: error: ‘int_least32_t’ was not declared in this scope
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:954:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                  ^~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:954:31: error: template argument 1 is invalid
   typedef atomic<int_least32_t>  atomic_int_least32_t;
                               ^
/usr/include/c++/7/atomic:960:18: error: ‘int_least64_t’ was not declared in this scope
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                  ^~~~~~~~~~~~~
/usr/include/c++/7/atomic:960:18: note: suggested alternative: ‘int_fast64_t’
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                  ^~~~~~~~~~~~~
                  int_fast64_t
/usr/include/c++/7/atomic:960:31: error: template argument 1 is invalid
   typedef atomic<int_least64_t>  atomic_int_least64_t;
                               ^
/usr/include/c++/7/atomic:963:18: error: ‘uint_least64_t’ was not declared in this scope
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                  ^~~~~~~~~~~~~~
/usr/include/c++/7/atomic:963:18: note: suggested alternative: ‘uint_least32_t’
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                  ^~~~~~~~~~~~~~
                  uint_least32_t
/usr/include/c++/7/atomic:963:32: error: template argument 1 is invalid
   typedef atomic<uint_least64_t> atomic_uint_least64_t;
                                ^
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:7:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h: In function ‘at::Tensor dl_lib::ROIAlign_forward(const at::Tensor&, const at::Tensor&, float, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h:62:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (input.type().is_cuda()) {
                  ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:7:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h: In function ‘at::Tensor dl_lib::ROIAlign_backward(const at::Tensor&, const at::Tensor&, float, int, int, int, int, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/ROIAlign/ROIAlign.h:98:17: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (grad.type().is_cuda()) {
                 ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:8:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h: In function ‘int dl_lib::deform_conv_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, int)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:134:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (input.type().is_cuda()) {
                  ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:136:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:136:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:137:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:137:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:8:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h: In function ‘int dl_lib::deform_conv_backward_input(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, int)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:182:23: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (gradOutput.type().is_cuda()) {
                       ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:184:28: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
                            ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:184:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:185:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:185:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:186:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:186:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:8:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h: In function ‘int dl_lib::deform_conv_backward_filter(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, float, int)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:232:23: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (gradOutput.type().is_cuda()) {
                       ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:234:28: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
                            ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:234:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:235:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:235:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:8:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h: In function ‘void dl_lib::modulated_deform_conv_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:282:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (input.type().is_cuda()) {
                  ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:284:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:284:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:285:27: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
                           ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:285:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:286:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:286:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:8:0:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h: In function ‘void dl_lib::modulated_deform_conv_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, bool)’:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:339:24: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   if (grad_output.type().is_cuda()) {
                        ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:341:28: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
                            ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:341:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:342:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:342:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:343:27: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
                           ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:343:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Device.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:344:29: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
                             ^
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/macros/Macros.h:141:65: note: in definition of macro ‘C10_UNLIKELY’
 #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                 ^~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:262:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
   if (C10_UNLIKELY_OR_CONST(!(cond))) {                     \
       ^~~~~~~~~~~~~~~~~~~~~
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:273:32: note: in expansion of macro ‘TORCH_CHECK_WITH’
 #define TORCH_CHECK(cond, ...) TORCH_CHECK_WITH(Error, cond, __VA_ARGS__)
                                ^~~~~~~~~~~~~~~~
/home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/deformable/deform_conv.h:344:5: note: in expansion of macro ‘TORCH_CHECK’
     TORCH_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
     ^
In file included from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
                 from /home/noob/anaconda3/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /home/noob/projects/PycharmProjects/CenterNet-better-master/dl_lib/layers/vision.cpp:5:
/home/noob/anaconda3/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
   DeprecatedTypeProperties & type() const {
                              ^~~~
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "/home/noob/anaconda3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1423, in _run_ninja_build
    check=True)
  File "/home/noob/anaconda3/lib/python3.7/subprocess.py", line 512, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/noob/projects/PycharmProjects/CenterNet-better-master/setup.py", line 98, in <module>
    scripts=["tools/dl_train", "tools/dl_test"],
  File "/home/noob/anaconda3/lib/python3.7/site-packages/setuptools/__init__.py", line 144, in setup
    return distutils.core.setup(**attrs)
  File "/home/noob/anaconda3/lib/python3.7/distutils/core.py", line 148, in setup
    dist.run_commands()
  File "/home/noob/anaconda3/lib/python3.7/distutils/dist.py", line 966, in run_commands
    self.run_command(cmd)
  File "/home/noob/anaconda3/lib/python3.7/distutils/dist.py", line 985, in run_command
    cmd_obj.run()
  File "/home/noob/anaconda3/lib/python3.7/site-packages/setuptools/command/develop.py", line 38, in run
    self.install_for_development()
  File "/home/noob/anaconda3/lib/python3.7/site-packages/setuptools/command/develop.py", line 140, in install_for_development
    self.run_command('build_ext')
  File "/home/noob/anaconda3/lib/python3.7/distutils/cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "/home/noob/anaconda3/lib/python3.7/distutils/dist.py", line 985, in run_command
    cmd_obj.run()
  File "/home/noob/anaconda3/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 87, in run
    _build_ext.run(self)
  File "/home/noob/anaconda3/lib/python3.7/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
    _build_ext.build_ext.run(self)
  File "/home/noob/anaconda3/lib/python3.7/distutils/command/build_ext.py", line 340, in run
    self.build_extensions()
  File "/home/noob/anaconda3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 603, in build_extensions
    build_ext.build_extensions(self)
  File "/home/noob/anaconda3/lib/python3.7/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
    _build_ext.build_ext.build_extensions(self)
  File "/home/noob/anaconda3/lib/python3.7/distutils/command/build_ext.py", line 449, in build_extensions
    self._build_extensions_serial()
  File "/home/noob/anaconda3/lib/python3.7/distutils/command/build_ext.py", line 474, in _build_extensions_serial
    self.build_extension(ext)
  File "/home/noob/anaconda3/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 208, in build_extension
    _build_ext.build_extension(self, ext)
  File "/home/noob/anaconda3/lib/python3.7/distutils/command/build_ext.py", line 534, in build_extension
    depends=ext.depends)
  File "/home/noob/anaconda3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 437, in unix_wrap_ninja_compile
    with_cuda=with_cuda)
  File "/home/noob/anaconda3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1163, in _write_ninja_file_and_compile_objects
    error_prefix='Error compiling objects for extension')
  File "/home/noob/anaconda3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1436, in _run_ninja_build
    raise RuntimeError(message)
RuntimeError: Error compiling objects for extension
----------------------------------------

ERROR: Command errored out with exit status 1: /home/noob/anaconda3/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/noob/projects/PycharmProjects/CenterNet-better-master/setup.py'"'"'; file='"'"'/home/noob/projects/PycharmProjects/CenterNet-better-master/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.
(

相对于原版的改进

ResNet-18 map：29.8 确实厉害
请问下这里使用了dcn吗？从代码里没看到
再就是打高斯核和数据增强同原版有改进吗？

infrence data without normalization？

CenterNet-better/dl_lib/network/centernet.py

Lines 145 to 152 in 2194a15

 pad_value = [-x / y for x, y in zip(self.mean, self.std)] 

 aligned_img = torch.Tensor(pad_value).reshape((1, -1, 1, 1)).expand(n, c, new_h, new_w) 

 aligned_img = aligned_img.to(images.tensor.device) 

 pad_w, pad_h = math.ceil((new_w - w) / 2), math.ceil((new_h - h) / 2) 

 aligned_img[..., pad_h:h + pad_h, pad_w:w + pad_w] = images.tensor 

 features = self.backbone(aligned_img)

hi,
the ‘aligned_img’ data that put into the backone is simply copy of the 'images' without being normalized with 'self.mean & self.std', is it right or a bug?

Error during build

I use a Conda environment where I installed pytorch 1.3.1 gpu, but I have follow error when I start setup.py

ERROR: Command errored out with exit status 1:
 command: /home/ulix/anaconda3/envs/centerenetbetter/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/setup.py'"'"'; __file__='"'"'/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' develop --no-deps
     cwd: /media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/
Complete output (17 lines):
running develop
running egg_info
writing dl_lib.egg-info/PKG-INFO
writing dependency_links to dl_lib.egg-info/dependency_links.txt
writing requirements to dl_lib.egg-info/requires.txt
writing top-level names to dl_lib.egg-info/top_level.txt
reading manifest file 'dl_lib.egg-info/SOURCES.txt'
writing manifest file 'dl_lib.egg-info/SOURCES.txt'
running build_ext
building 'dl_lib._C' extension
gcc -pthread -B /home/ulix/anaconda3/envs/centerenetbetter/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/dl_lib/layers -I/home/ulix/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/lib/include -I/home/ulix/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/lib/include/TH -I/home/ulix/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/lib/include/THC -I/home/ulix/anaconda3/envs/centerenetbetter/include/python3.6m -c /media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/dl_lib/layers/vision.cpp -o build/temp.linux-x86_64-3.6/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/dl_lib/layers/vision.o -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/dl_lib/layers/vision.cpp:5:10: fatal error: torch/types.h: No such file or directory
 #include <torch/types.h>
          ^~~~~~~~~~~~~~~
compilation terminated.
error: command 'gcc' failed with exit status 1
----------------------------------------

ERROR: Command errored out with exit status 1: /home/ulix/anaconda3/envs/centerenetbetter/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/setup.py'"'"'; file='"'"'/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n(centerenetbetter) ulix@ulix-Strix-17-GL703GE:/media/ulix/DATA1/Progetti/Inventio/InMindSO/CenterNet-better$ ^Cfor full command output.

About padding operation(迷之操作) during inference!

Feng wang:

I tried to understand padding operations during inference but failed. You should give an explanation.

Following the original CenterNet implementation, replacing the padding with CenterAffine, mAP drops to 28% compared with original 34.4% performance!

You are expected to give the reason!

Get Error: All Ap,AR is 0.

Hi, thanks for your great work.
I have some questions:
My config: in centernet.res50.coco.512size: IMS_PER_BATCH=4,NUM_WORKERS=2,.Other config is not change.
My results: All Ap,AR is 0.
thanks

some question about config file

hello, this is a great work, i try to customize a rotate-centernet based on your work. but i don't understand MODEL.CENTERNET.TENSOR_DIM in config file in every playground. can you please explain the meaning of it ?

请问一下网络的后处理在哪个部分

rt。。。我看了下test里直接把model结果输出了？不是应该有个maxpool操作加上topk排序吗....我没有找到这个方面的实现？是有什么考虑吗？

About the initialization model

In the original paper of CenterNet, the authors finetune the model from ExtremeNet-trained model instead of the ImageNet pretrained model or training from scratch. Which strategy is used in this repo and do you know the difference of performance among these strategies?
Thank you very much!

when will the code support DLA backbone?

Hi, thanks for your great work. When will the DLA backbone be supported?

how to use multi scale test?

in original code can set test_scales=xxx, how to set this in this code.
thanks!

PermissionError: [Errno 13] Permission denied: '/data'

I meet PermissionError: [Errno 13] Permission denied: '/data' when I train my model. And I get the path which cause this error:
/data/Outputs/model_logs/playground/centernet.res18.coco.512size

Then I run chmod 777 /data,it also throw that error.

The detail error is below:

soft link to /data/Outputs/model_logs/playground/centernet.res18.coco.512size
Command Line Args: Namespace(dist_url='tcp://127.0.0.1:50163', eval_only=False, machine_rank=0, num_gpus=2, num_machines=1, opts=[], resume=False)
Traceback (most recent call last):
File "/home/wangqinyu/STR/CenterNet-better/tools/train_net.py", line 125, in
args=(args,),
File "/home/wangqinyu/STR/CenterNet-better/dl_lib/engine/launch.py", line 50, in launch
daemon=False,
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
while not context.join():
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 150, in join
raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error:
Traceback (most recent call last):
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap
fn(i, *args)
File "/home/wangqinyu/STR/CenterNet-better/dl_lib/engine/launch.py", line 85, in _distributed_worker
main_func(*args)
File "/home/wangqinyu/STR/CenterNet-better/tools/train_net.py", line 79, in main
cfg, logger = default_setup(config, args)
File "/home/wangqinyu/STR/CenterNet-better/dl_lib/engine/defaults.py", line 95, in default_setup
PathManager.mkdirs(output_dir)
File "/home/wangqinyu/STR/CenterNet-better/dl_lib/utils/file_io.py", line 447, in mkdirs
return PathManager.__get_path_handler(path)._mkdirs(path)
File "/home/wangqinyu/STR/CenterNet-better/dl_lib/utils/file_io.py", line 253, in _mkdirs
os.makedirs(path, exist_ok=True)
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/os.py", line 213, in makedirs
makedirs(head, exist_ok=exist_ok)
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/os.py", line 213, in makedirs
makedirs(head, exist_ok=exist_ok)
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/os.py", line 213, in makedirs
makedirs(head, exist_ok=exist_ok)
[Previous line repeated 1 more time]
File "/home/wangqinyu/anaconda3/envs/STR/lib/python3.7/os.py", line 223, in makedirs
mkdir(name, mode)
PermissionError: [Errno 13] Permission denied: '/data'

No module named 'brainpp'

Hi I just had the following error when testing the res18 downloaded model

CenterNet-better/dl_lib/utils/file_io.py", line 13, in <module>
    from brainpp import oss
ModuleNotFoundError: No module named 'brainpp'

I have all the dependencies installed.
Would you know what is the problem?

I followed all instructions in "Get Started" but it still can not find dl_train command

Thanks for your contribution! I know this is a noob question... but it indeed confused me...
[13:42:54]:think@~/centernet.res18.coco.512size$dl_train --num-gpus 1
If 'dl_train' is not a typo you can use command-not-found to lookup the package that contains it, like this:
cnf dl_train

I have already done:
pip install cython; pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
pip install -e .

I have:
python 3.6.12
gcc 7.5.0
pytorch 1.8.0
torchvision 0.9.0

Thanks again for your patience in advance!

How to train a model with the custom dataset(coco style or voc style)?

First thank you for your repo.
My data is a voc style,and have translate it to coco style,but the class number of the dataset is only 1,What I need do to have a train with your repo?

I'm interested in why it performs better

install error gcc -std=gnu99: No such file or directory

在gcc 4.9 5.2 cuda 9.0 10.1下均会报错：
ERROR: Command errored out with exit status 1:
command: /search/odin/hongyuan/anaconda3/envs/py13/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/search/odin/hongyuan/CenterNet-better/setup.py'"'"'; file='"'"'/search/odin/hongyuan/CenterNet-better/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps
cwd: /search/odin/hongyuan/CenterNet-better/
Complete output (19 lines):
running develop
running egg_info
writing dl_lib.egg-info/PKG-INFO
writing dependency_links to dl_lib.egg-info/dependency_links.txt
writing requirements to dl_lib.egg-info/requires.txt
writing top-level names to dl_lib.egg-info/top_level.txt
reading manifest file 'dl_lib.egg-info/SOURCES.txt'
writing manifest file 'dl_lib.egg-info/SOURCES.txt'
running build_ext
building 'dl_lib.C' extension
gcc -std=gnu99 -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/search/odin/hongyuan/CenterNet-better/dl_lib/layers -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/TH -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/THC -I/search/odin/hongyuan/cuda-9.0/include -I/search/odin/hongyuan/anaconda3/envs/py13/include/python3.7m -c /search/odin/hongyuan/CenterNet-better/dl_lib/layers/vision.cpp -o build/temp.linux-x86_64-3.7/search/odin/hongyuan/CenterNet-better/dl_lib/layers/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-std=gnu99’ is valid for C/ObjC but not for C++
gcc -std=gnu99 -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/search/odin/hongyuan/CenterNet-better/dl_lib/layers -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/TH -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/THC -I/search/odin/hongyuan/cuda-9.0/include -I/search/odin/hongyuan/anaconda3/envs/py13/include/python3.7m -c /search/odin/hongyuan/CenterNet-better/dl_lib/layers/ROIAlign/ROIAlign_cpu.cpp -o build/temp.linux-x86_64-3.7/search/odin/hongyuan/CenterNet-better/dl_lib/layers/ROIAlign/ROIAlign_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
cc1plus: warning: command line option ‘-std=gnu99’ is valid for C/ObjC but not for C++
/search/odin/hongyuan/cuda-9.0/bin/nvcc -DWITH_CUDA -I/search/odin/hongyuan/CenterNet-better/dl_lib/layers -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/TH -I/search/odin/hongyuan/anaconda3/envs/py13/lib/python3.7/site-packages/torch/include/THC -I/search/odin/hongyuan/cuda-9.0/include -I/search/odin/hongyuan/anaconda3/envs/py13/include/python3.7m -c /search/odin/hongyuan/CenterNet-better/dl_lib/layers/ROIAlign/ROIAlign_cuda.cu -o build/temp.linux-x86_64-3.7/search/odin/hongyuan/CenterNet-better/dl_lib/layers/ROIAlign/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS_ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -ccbin=gcc -std=gnu99 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -gencode=arch=compute_61,code=sm_61 -std=c++11
gcc -std=gnu99: No such file or directory
error: command '/search/odin/hongyuan/cuda-9.0/bin/nvcc' failed with exit status 1
----------------------------------------
ERROR: Command errored out with exit status 1: /search/odin/hongyuan/anaconda3/envs/py13/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/search/odin/hongyuan/CenterNet-better/setup.py'"'"'; file='"'"'/search/odin/hongyuan/CenterNet-better/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.

how long did u trained the model when get a reasonable result?

is this loss normal on 1 GPU?

[03/11 14:38:25 c2.utils.events]: eta: 3 days, 15:40:16  iter: 22020  total_loss: 6.084  loss_cls: 4.101  loss_box_wh: 1.746  loss_center_reg: 0.247  time: 0.4291  data_time: 0.0049  lr: 0.002500  max_mem: 4794M

and here is my solver settings:

 SOLVER=dict(
        OPTIMIZER=dict(
            NAME="SGD",
            BASE_LR=0.0025,
            WEIGHT_DECAY=8e-4,
        ),
        LR_SCHEDULER=dict(
            GAMMA=0.1,
            STEPS=(81000, 108000),
            MAX_ITER=826000,
            WARMUP_ITERS=1000,
        ),
        IMS_PER_BATCH=8,
    ),

So have to training 3 days to get a converge result?

How to adjust checkpoint frequency

Thanks to your repo, i've trained model successfull on my custom dataset. It's very helpfull and very well. However, like the title, i don't know how to set the checkpoint frequency. Can you help me. Thanks

training and network config is missing?

"from config import config" in train_net.py, but I can't find the config file.
And where cfg.build_backbone, cfg.build_upsample_layers, cfg.build_head are ?

生成真值index

看起来可以用中文交流？
在 dl_lib/network/generator/centernet_gt.py 的 CenterNetGT 类的 generate 方法中，

gt_index[:num_boxes] = centers_int[..., 1] * output_size[0] + centers_int[..., 0]

按理解，output_size[0] 是输出特征图的高度，output_size[1] 是宽度吧？centers_int[1] 是 box 中心点的 y，那这块的 index 计算是不是应该是

centers_int[..., 1] * output_size[1] + centers_int[..., 0]

虽然因为out_size 的高宽一样，对结果没有影响。

4GPU training with resnet18-centernet

Hi
I tried to train CenterNet resnet18 with 4GPU and batchsize 128. The network can not converge.
Did you met the seem problem?

What is the environment of your performance

I'm wondering your test environment. Is it V100 or Tesla Xp

change backbone

老哥你好，如果我想在你的代码基础之上做一些修改，比如更换backbone，那我应该怎么做，你能在你有空的时候给一些指导吗，先谢谢老哥了

About Learning Rate

Hi, this repo is great.
When I was reproducing it, I found that in official CenterNet repo and paper, the base learning rate is 5e-4. But your learning rate is 0.02. Why your learning rate is much larger? And have you ever tried smaller learning rate?

How to train my own data set?

How can I train my own detection data set? Which parts should I probably modify?

训练的初始化模型请问是怎么load的？

有没有可以离线下载的链接? 另外如果想用 python xxxx.py 的方式启动要怎么操作？

test resolution (输入尺度带来的增益)

Hi Feng, I'd like to first appreciate this implementation. However, as mentioned in issue #35 , the processing of inference is different from the original Centernet. Specifically, the original algo. resize the image to (512, 512), and then the decoded results are mapped into the original sizes. But in this implementation, the input is padded and then sent to the network. I think the major performance gain is brought by the larger resolution, and I change the inference process like Centernet ( steps: resize the image to (512, 512) -> forward -> decode on the heatmap (128x128) -> resize via the original width/height)， the inference results are listed as follows.

Model	Inference Size (512x512)	Reported (Pad <=32)	Centernet
Res18-DCN	28.8	29.8	28.1
Res50-DCN	33.9	34.9	-
Res101-DCN	35.4	36.8	34.6

Compared to the official implementation, the performance gain is about 0.8 points.

How to train this model on my custome dataset

I've read the previous issues and i've known that this capo set dataset is same with detectron2. So i found that i can use these line of codes:

register_coco_instances("my_dataset_train", {}, PATH_TO_TRAIN_JSON, PATH_TO_TRAIN_IMAGES)
register_coco_instances("my_dataset_val",` {}, PATH_TO_VAL_JSON, PATH_TO_VAL_IMAGES)

but i don't know where to put those line of codes. Because you said that train model by dl_train .... and i don't understand that. i've try to put those codes in config.py in init function but it doesn't work. Please help me

输入尺寸问题

你好，我在centernet.py line153下面打印up_fmap的尺寸（使用test_net.py）

  up_fmap = self.upsample(features)

  print(up_fmap.size())

，发现输出为
torch.Size([1, 64, 128, 168])
torch.Size([1, 64, 128, 168])
torch.Size([1, 64, 112, 168])
torch.Size([1, 64, 128, 168])
torch.Size([1, 64, 168, 96])
torch.Size([1, 64, 168, 160])
torch.Size([1, 64, 168, 128])
torch.Size([1, 64, 112, 168])
torch.Size([1, 64, 136, 168])
torch.Size([1, 64, 168, 112])
torch.Size([1, 64, 168, 112])

这部分尺寸输出不应该是128吗，我没有找到输入resize为512那部分代码？请问这个复现不是基于固定尺寸（输入512，输出128）的吗?

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

	pad_value = [-x / y for x, y in zip(self.mean, self.std)]
	aligned_img = torch.Tensor(pad_value).reshape((1, -1, 1, 1)).expand(n, c, new_h, new_w)
	aligned_img = aligned_img.to(images.tensor.device)

	pad_w, pad_h = math.ceil((new_w - w) / 2), math.ceil((new_h - h) / 2)
	aligned_img[..., pad_h:h + pad_h, pad_w:w + pad_w] = images.tensor

	features = self.backbone(aligned_img)