Comments (19)
有試過 https://github.com/JunnYu/mish-cuda 嗎
from scaledyolov4.
使用的RAM差很多(約1.8倍) 還有速度差很多(約1.2倍)
from scaledyolov4.
第一位编译不过去的可以这么操作,把external/CUDAApplyUtils.cuh拷贝到csrc目录下:
cp external/CUDAApplyUtils.cuh csrc/
from scaledyolov4.
也尝试过,也是相同的error,我可不可以在models/ common.py
中基于Pytorch重新给个Mish激活函数的定义?如下:
# no pretrain
# from mish_cuda import MishCuda as Mish
# pretrain
#from mc.build.lib.mish_mish import MishCuda as Mish
# 实在装不上mish-cuda,用pytorch自己实现
class Mish(nn.Module):
def __init__(self):
super().__init__()
def forward(self,x):
x = x * (torch.tanh(F.softplus(x)))
return x
这样我训练是可以正常训练的,但是不确定这个Mish-cuda和Mish激活函数的区别在哪,求大佬答疑解惑!
from scaledyolov4.
好的,明白!
from scaledyolov4.
GPU=2080s
在镜像pytorch:20.06-py3下使用https://github.com/thomasbrandon/mish-cuda不能正常编译,https://github.com/JunnYu/mish-cuda则可以。
from scaledyolov4.
GPU=2080s
在镜像pytorch:20.06-py3下使用https://github.com/thomasbrandon/mish-cuda不能正常编译,https://github.com/JunnYu/mish-cuda则可以。
这边也是同样的情况,2080ti,pytorch:20.06-py3镜像,驱动版本450,用https://github.com/thomasbrandon/mish-cuda的一直提示编译失败,换成https://github.com/JunnYu/mish-cuda则可以。
thomasbrandon版本的编译失败报错信息:
running build
running build_py
creating build
creating build/lib.linux-x86_64-3.6
creating build/lib.linux-x86_64-3.6/mish_cuda
copying src/mish_cuda/__init__.py -> build/lib.linux-x86_64-3.6/mish_cuda
running egg_info
creating src/mish_cuda.egg-info
writing src/mish_cuda.egg-info/PKG-INFO
writing dependency_links to src/mish_cuda.egg-info/dependency_links.txt
writing requirements to src/mish_cuda.egg-info/requires.txt
writing top-level names to src/mish_cuda.egg-info/top_level.txt
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
reading manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
running build_ext
building 'mish_cuda._C' extension
creating /mish-cuda/build/temp.linux-x86_64-3.6
creating /mish-cuda/build/temp.linux-x86_64-3.6/csrc
Emitting ninja build file /mish-cuda/build/temp.linux-x86_64-3.6/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/3] /usr/local/cuda/bin/nvcc -Iexternal -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/mish_kernel.cu -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_52,code=sm_52 -std=c++14
FAILED: /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_kernel.o
/usr/local/cuda/bin/nvcc -Iexternal -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/mish_kernel.cu -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_52,code=sm_52 -std=c++14
/mish-cuda/csrc/mish_kernel.cu:3:10: fatal error: CUDAApplyUtils.cuh: No such file or directory
#include "CUDAApplyUtils.cuh"
^~~~~~~~~~~~~~~~~~~~
compilation terminated.
[2/3] c++ -MMD -MF /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_cpu.o.d -pthread -B /opt/conda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -Iexternal -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/mish_cpu.cpp -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
[3/3] c++ -MMD -MF /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_cuda.o.d -pthread -B /opt/conda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -Iexternal -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/mish_cuda.cpp -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/mish_cuda.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1471, in _run_ninja_build
check=True)
File "/opt/conda/lib/python3.6/subprocess.py", line 438, 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 "setup.py", line 30, in <module>
'build_ext': BuildExtension
File "/opt/conda/lib/python3.6/site-packages/setuptools/__init__.py", line 161, in setup
return distutils.core.setup(**attrs)
File "/opt/conda/lib/python3.6/distutils/core.py", line 148, in setup
dist.run_commands()
File "/opt/conda/lib/python3.6/distutils/dist.py", line 955, in run_commands
self.run_command(cmd)
File "/opt/conda/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/opt/conda/lib/python3.6/distutils/command/build.py", line 135, in run
self.run_command(cmd_name)
File "/opt/conda/lib/python3.6/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/opt/conda/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/opt/conda/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 87, in run
_build_ext.run(self)
File "/opt/conda/lib/python3.6/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
_build_ext.build_ext.run(self)
File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 633, in build_extensions
build_ext.build_extensions(self)
File "/opt/conda/lib/python3.6/site-packages/Cython/Distutils/old_build_ext.py", line 194, in build_extensions
self.build_extension(ext)
File "/opt/conda/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 208, in build_extension
_build_ext.build_extension(self, ext)
File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
depends=ext.depends)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 462, in unix_wrap_ninja_compile
with_cuda=with_cuda)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1211, in _write_ninja_file_and_compile_objects
error_prefix='Error compiling objects for extension')
File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1484, in _run_ninja_build
raise RuntimeError(message)
RuntimeError: Error compiling objects for extension
JunnYu的编译成功信息:
running build
running build_py
creating build
creating build/lib.linux-x86_64-3.6
creating build/lib.linux-x86_64-3.6/mish_cuda
copying src/mish_cuda/__init__.py -> build/lib.linux-x86_64-3.6/mish_cuda
running egg_info
creating src/mish_cuda.egg-info
writing src/mish_cuda.egg-info/PKG-INFO
writing dependency_links to src/mish_cuda.egg-info/dependency_links.txt
writing requirements to src/mish_cuda.egg-info/requires.txt
writing top-level names to src/mish_cuda.egg-info/top_level.txt
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
reading manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
running build_ext
building 'mish_cuda._C' extension
creating /mish-cuda/build/temp.linux-x86_64-3.6
creating /mish-cuda/build/temp.linux-x86_64-3.6/csrc
creating /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cpu
creating /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda
Emitting ninja build file /mish-cuda/build/temp.linux-x86_64-3.6/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/3] c++ -MMD -MF /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cpu/mish_cpu.o.d -pthread -B /opt/conda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/cpu/mish_cpu.cpp -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cpu/mish_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
[2/3] c++ -MMD -MF /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda/mish_cuda.o.d -pthread -B /opt/conda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/cuda/mish_cuda.cpp -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda/mish_cuda.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
[3/3] /usr/local/cuda/bin/nvcc -I/opt/conda/lib/python3.6/site-packages/torch/include -I/opt/conda/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/opt/conda/lib/python3.6/site-packages/torch/include/TH -I/opt/conda/lib/python3.6/site-packages/torch/include/THC -I/usr/local/cuda/include -I/opt/conda/include/python3.6m -c -c /mish-cuda/csrc/cuda/mish_kernel.cu -o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=1 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_52,code=sm_52 -gencode=arch=compute_60,code=sm_60 -std=c++14
g++ -pthread -shared -B /opt/conda/compiler_compat -L/opt/conda/lib -Wl,-rpath=/opt/conda/lib -Wl,--no-as-needed -Wl,--sysroot=/ /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cpu/mish_cpu.o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda/mish_cuda.o /mish-cuda/build/temp.linux-x86_64-3.6/csrc/cuda/mish_kernel.o -L/opt/conda/lib/python3.6/site-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.6/mish_cuda/_C.cpython-36m-x86_64-linux-gnu.so
running install
running bdist_egg
installing library code to build/bdist.linux-x86_64/egg
running install_lib
creating build/bdist.linux-x86_64
creating build/bdist.linux-x86_64/egg
creating build/bdist.linux-x86_64/egg/mish_cuda
copying build/lib.linux-x86_64-3.6/mish_cuda/_C.cpython-36m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/mish_cuda
copying build/lib.linux-x86_64-3.6/mish_cuda/__init__.py -> build/bdist.linux-x86_64/egg/mish_cuda
byte-compiling build/bdist.linux-x86_64/egg/mish_cuda/__init__.py to __init__.cpython-36.pyc
creating stub loader for mish_cuda/_C.cpython-36m-x86_64-linux-gnu.so
byte-compiling build/bdist.linux-x86_64/egg/mish_cuda/_C.py to _C.cpython-36.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/not-zip-safe -> build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/requires.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying src/mish_cuda.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt
creating dist
creating 'dist/mish_cuda-0.0.3-py3.6-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
Processing mish_cuda-0.0.3-py3.6-linux-x86_64.egg
creating /opt/conda/lib/python3.6/site-packages/mish_cuda-0.0.3-py3.6-linux-x86_64.egg
Extracting mish_cuda-0.0.3-py3.6-linux-x86_64.egg to /opt/conda/lib/python3.6/site-packages
Adding mish-cuda 0.0.3 to easy-install.pth file
Installed /opt/conda/lib/python3.6/site-packages/mish_cuda-0.0.3-py3.6-linux-x86_64.egg
Processing dependencies for mish-cuda==0.0.3
Searching for torch==1.6.0a0+9907a3e
Best match: torch 1.6.0a0+9907a3e
Adding torch 1.6.0a0+9907a3e to easy-install.pth file
Installing convert-caffe2-to-onnx script to /opt/conda/bin
Installing convert-onnx-to-caffe2 script to /opt/conda/bin
Using /opt/conda/lib/python3.6/site-packages
Searching for future==0.18.2
Best match: future 0.18.2
Adding future 0.18.2 to easy-install.pth file
Installing futurize script to /opt/conda/bin
Installing pasteurize script to /opt/conda/bin
Using /opt/conda/lib/python3.6/site-packages
Searching for numpy==1.18.1
Best match: numpy 1.18.1
Adding numpy 1.18.1 to easy-install.pth file
Installing f2py script to /opt/conda/bin
Installing f2py3 script to /opt/conda/bin
Installing f2py3.6 script to /opt/conda/bin
Using /opt/conda/lib/python3.6/site-packages
Finished processing dependencies for mish-cuda==0.0.3
from scaledyolov4.
@DataXujing 请问您这边安装好mish-cuda了吗?
@WongKinYiu 如果换成JunnYu版本的mish-cuda,还需要修改哪些代码吗?
from scaledyolov4.
不用pretrianed model就都不用改
要用的話就要把有出現mish_cuda的部分都改成mish_mish
from scaledyolov4.
不需要用mosaic怎么修改
from scaledyolov4.
"JunnYu"版本安装成功。(CentOS 8.3 ,Driver Version: 455.45.01,CUDA 10.1 ,TITAN X,python 3.6.8,torch 1.5.0,gcc version 8.4.1 )
方式:
1、git clone到本地;
2、cd 到根目录;
3、确保已安装gcc的c++支持(dnf install gcc-c++);
4、运行:python setup.py install
from scaledyolov4.
JunnYu's mish version compiled successfully!, https://github.com/JunnYu/mish-cuda (Ubuntu20.04, Drivier: 460.27.04, CUDA:11.2, Pytorch1.8)
from scaledyolov4.
`(pytorch) xiaopeng@xiaopeng-HP-Z800-Workstation:~/ScaledYOLOv4-yolov4-csp/mish-cuda$ python setup.py build install
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/extension.py:131: UserWarning: Unknown Extension options: 'headers'
warnings.warn(msg)
running build
running build_py
creating build
creating build/lib.linux-x86_64-3.7
creating build/lib.linux-x86_64-3.7/mish_cuda
copying src/mish_cuda/init.py -> build/lib.linux-x86_64-3.7/mish_cuda
running egg_info
creating src/mish_cuda.egg-info
writing src/mish_cuda.egg-info/PKG-INFO
writing dependency_links to src/mish_cuda.egg-info/dependency_links.txt
writing requirements to src/mish_cuda.egg-info/requires.txt
writing top-level names to src/mish_cuda.egg-info/top_level.txt
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
reading manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
running build_ext
building 'mish_cuda.C' extension
creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7
creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc
creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu
creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda
Emitting ninja build file /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/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)
[1/3] :/usr/local/cuda/bin/nvcc -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_kernel.cu -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
FAILED: /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o
:/usr/local/cuda/bin/nvcc -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_kernel.cu -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/usr/local/cuda/bin/nvcc: not found
[2/3] c++ -MMD -MF /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu/mish_cpu.o.d -pthread -B /home/xiaopeng/miniconda3/envs/pytorch/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cpu/mish_cpu.cpp -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu/mish_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 /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/CPUApplyUtils.h:3,
from /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cpu/mish_cpu.cpp:3:
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
84 | #pragma omp parallel for if ((end - begin) >= grain_size)
|
[3/3] c++ -MMD -MF /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_cuda.o.d -pthread -B /home/xiaopeng/miniconda3/envs/pytorch/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_cuda.cpp -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_cuda.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 /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:12,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_cuda.cpp:2:
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
84 | #pragma omp parallel for if ((end - begin) >= grain_size)
|
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1522, in _run_ninja_build
env=env)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/subprocess.py", line 512, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "setup.py", line 29, in
cmdclass={'build_ext': BuildExtension})
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/init.py", line 153, in setup
return distutils.core.setup(**attrs)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build.py", line 135, in run
self.run_command(cmd_name)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 653, in build_extensions
build_ext.build_extensions(self)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 196, in build_extension
_build_ext.build_extension(self, ext)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 534, in build_extension
depends=ext.depends)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 482, in unix_wrap_ninja_compile
with_cuda=with_cuda)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1238, in _write_ninja_file_and_compile_objects
error_prefix='Error compiling objects for extension')
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1538, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension
`
@trikim 我用的是cuda11.0,ubuntu20.04.两个版本的mish都试了。都不行。
你碰见过这个错误吗
@WongKinYiu
@DataXujing
@JustinhoCHN
from scaledyolov4.
也尝试过,也是相同的error,我可不可以在
models/ common.py
中基于Pytorch重新给个Mish激活函数的定义?如下:# no pretrain # from mish_cuda import MishCuda as Mish # pretrain #from mc.build.lib.mish_mish import MishCuda as Mish # 实在装不上mish-cuda,用pytorch自己实现 class Mish(nn.Module): def __init__(self): super().__init__() def forward(self,x): x = x * (torch.tanh(F.softplus(x))) return x
这样我训练是可以正常训练的,但是不确定这个Mish-cuda和Mish激活函数的区别在哪,求大佬答疑解惑!
@DataXujing 我在实验室另一台电脑上成功了。pytorch1.4 cuda10.1
但是我自己的服务器却失败了。
from scaledyolov4.
也尝试过,也是相同的error,我可不可以在
models/ common.py
中基于Pytorch重新给个Mish激活函数的定义?如下:# no pretrain # from mish_cuda import MishCuda as Mish # pretrain #from mc.build.lib.mish_mish import MishCuda as Mish # 实在装不上mish-cuda,用pytorch自己实现 class Mish(nn.Module): def __init__(self): super().__init__() def forward(self,x): x = x * (torch.tanh(F.softplus(x))) return x
这样我训练是可以正常训练的,但是不确定这个Mish-cuda和Mish激活函数的区别在哪,求大佬答疑解惑!
我想请问一下 这个F是什么
from scaledyolov4.
`(pytorch) xiaopeng@xiaopeng-HP-Z800-Workstation:~/ScaledYOLOv4-yolov4-csp/mish-cuda$ python setup.py build install
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/extension.py:131: UserWarning: Unknown Extension options: 'headers'
warnings.warn(msg)
running build
running build_py
creating build
creating build/lib.linux-x86_64-3.7
creating build/lib.linux-x86_64-3.7/mish_cuda
copying src/mish_cuda/init.py -> build/lib.linux-x86_64-3.7/mish_cuda
running egg_info
creating src/mish_cuda.egg-info
writing src/mish_cuda.egg-info/PKG-INFO
writing dependency_links to src/mish_cuda.egg-info/dependency_links.txt
writing requirements to src/mish_cuda.egg-info/requires.txt
writing top-level names to src/mish_cuda.egg-info/top_level.txt
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
reading manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
writing manifest file 'src/mish_cuda.egg-info/SOURCES.txt'
running build_ext
building 'mish_cuda.C' extension creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7 creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu creating /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda Emitting ninja build file /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/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) [1/3] :/usr/local/cuda/bin/nvcc -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_kernel.cu -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14 FAILED: /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o :/usr/local/cuda/bin/nvcc -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_kernel.cu -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_kernel.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' --expt-extended-lambda -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/usr/local/cuda/bin/nvcc: not found
[2/3] c++ -MMD -MF /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu/mish_cpu.o.d -pthread -B /home/xiaopeng/miniconda3/envs/pytorch/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cpu/mish_cpu.cpp -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cpu/mish_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 /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/CPUApplyUtils.h:3,
from /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cpu/mish_cpu.cpp:3:
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
84 | #pragma omp parallel for if ((end - begin) >= grain_size)
|
[3/3] c++ -MMD -MF /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_cuda.o.d -pthread -B /home/xiaopeng/miniconda3/envs/pytorch/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/TH -I/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/THC -I:/usr/local/cuda/include -I/home/xiaopeng/miniconda3/envs/pytorch/include/python3.7m -c -c /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_cuda.cpp -o /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/build/temp.linux-x86_64-3.7/csrc/cuda/mish_cuda.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 /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:12,
from /home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /home/xiaopeng/ScaledYOLOv4-yolov4-csp/mish-cuda/csrc/cuda/mish_cuda.cpp:2:
/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
84 | #pragma omp parallel for if ((end - begin) >= grain_size)
|
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1522, in _run_ninja_build
env=env)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/subprocess.py", line 512, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "setup.py", line 29, in
cmdclass={'build_ext': BuildExtension})
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/init.py", line 153, in setup
return distutils.core.setup(**attrs)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build.py", line 135, in run
self.run_command(cmd_name)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 653, in build_extensions
build_ext.build_extensions(self)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 196, in build_extension
_build_ext.build_extension(self, ext)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/distutils/command/build_ext.py", line 534, in build_extension
depends=ext.depends)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 482, in unix_wrap_ninja_compile
with_cuda=with_cuda)
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1238, in _write_ninja_file_and_compile_objects
error_prefix='Error compiling objects for extension')
File "/home/xiaopeng/miniconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1538, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension
`@trikim 我用的是cuda11.0,ubuntu20.04.两个版本的mish都试了。都不行。
你碰见过这个错误吗
@WongKinYiu
@DataXujing
@JustinhoCHN
兄弟我和你一样的错误,现在解决了吗?
from scaledyolov4.
@LoveMartina pytorh版本问题,需要1.5或者1.4,太新的不行。
from scaledyolov4.
修改CUDA_HOME=/usr/local/cuda/bin/nvcc 即可,我也遇到这个问题了,修改了CUDA_HOME就能完成编译了。
from scaledyolov4.
也尝试过,也是相同的error,我可不可以在
models/ common.py
中基于Pytorch重新给个Mish激活函数的定义?如下:# no pretrain # from mish_cuda import MishCuda as Mish # pretrain #from mc.build.lib.mish_mish import MishCuda as Mish # 实在装不上mish-cuda,用pytorch自己实现 class Mish(nn.Module): def __init__(self): super().__init__() def forward(self,x): x = x * (torch.tanh(F.softplus(x))) return x
这样我训练是可以正常训练的,但是不确定这个Mish-cuda和Mish激活函数的区别在哪,求大佬答疑解惑!
它可以工作,但不能使用预训练模型
from scaledyolov4.
Related Issues (20)
- Issue with reported confidence level of the single-cls scaled yolov4 csp implementation
- single GPU in training HOT 4
- RuntimeError: result type Float can't be cast to the desired output type long int HOT 2
- Fail to transfer .pt into .onnx
- Question about the loss function
- how to train the trick to achive goals?
- YOLOv4-P6 convert torch .pt to darknet .weights
- is there a mask(segmentation) branch for scaledYOLOv4 project?
- Train.py runtime error, Float can't be cast to the desired output type long int HOT 1
- wrong calculation of map
- Pretrained checkpoints?
- The fps of YOLOV4-CSP?
- why mish-cuda?
- When I run the test.py in docker, one issue appeared. HOT 2
- Could not download models
- Could not download pretrained models such as yolov4-p5.pt,yolov4-p6.pt,yolov4-p7.pt file
- I Could not download pretrained models such as yolov4-p5.pt,yolov4-p6.pt,yolov4-p7.pt file. Could you please help me.
- Error while training the yolov7 model _pickle.UnpicklingError: STACK_GLOBAL requires str HOT 2
- Looking for yolov4 weights HOT 2
- RuntimeError: Trying to create tensor with negative dimension -920509440: [-920509440]
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.
from scaledyolov4.