Comments (4)
The easiest way is to change data_root
and ann_file
of CocoTrain
and CocoVal
in https://github.com/zju3dv/snake/blob/master/lib/datasets/dataset_catalog.py
And then
python train_net.py --cfg_file snake/sbd_snake.yaml model custom_model train.dataset CocoTrain test.dataset CocoVal
python run.py --type evaluate --cfg_file snake/sbd_snake.yaml model custom_model train.dataset CocoTrain test.dataset CocoVal
python run.py --type visualize --cfg_file snake/sbd_snake.yaml model custom_model train.dataset CocoTrain test.dataset CocoVal
from snake.
Installed /ldap_shared/home/s_zyt/.pyenv/versions/anaconda3-2019.07/envs/snake/lib/python3.7/site-packages/apex-0.1-py3.7-linux-x86_64.egg
Processing dependencies for apex==0.1
Finished processing dependencies for apex==0.1
(anaconda3-2019.07/envs/snake) ➜ apex git:(master) cd ..
(anaconda3-2019.07/envs/snake) ➜ inseg cd code/snake
(anaconda3-2019.07/envs/snake) ➜ snake git:(master) ✗ ls
INSTALL.md README.md configs demo_images lib requirements.txt run.sh tools visualize.sh
LICENSE assets data external project_structure.md run.py test.sh train_net.py
(anaconda3-2019.07/envs/snake) ➜ snake git:(master) ✗ cd lib/csrc
(anaconda3-2019.07/envs/snake) ➜ csrc git:(master) ✗ ls
dcn_v2 extreme_utils roi_align_layer
(anaconda3-2019.07/envs/snake) ➜ csrc git:(master) ✗ cd dcn_v2
(anaconda3-2019.07/envs/snake) ➜ dcn_v2 git:(master) ✗ python setup.py build_ext --inplace
running build_ext
copying build/lib.linux-x86_64-3.7/_ext.cpython-37m-x86_64-linux-gnu.so ->
(anaconda3-2019.07/envs/snake) ➜ dcn_v2 git:(master) ✗ cd ../extreme_utils
(anaconda3-2019.07/envs/snake) ➜ extreme_utils git:(master) ✗ python setup.py build_ext --inplace
running build_ext
copying build/lib.linux-x86_64-3.7/_ext.cpython-37m-x86_64-linux-gnu.so ->
(anaconda3-2019.07/envs/snake) ➜ extreme_utils git:(master) ✗ cd ../roi_align_layer
(anaconda3-2019.07/envs/snake) ➜ roi_align_layer git:(master) ✗ l
total 7.1M
drwxr-xr-x 5 2014 504 4.0K Apr 22 08:57 .
drwxr-xr-x 5 2014 504 4.0K Apr 6 20:51 ..
-rw-r--r-- 1 2014 504 1.7K Apr 6 20:51 ROIAlign.h
-rwxr-xr-x 1 2014 504 7.0M Apr 22 08:57 _roi_align.cpython-37m-x86_64-linux-gnu.so
drwxr-xr-x 4 2014 504 4.0K Apr 22 08:57 build
drwxr-xr-x 2 2014 504 4.0K Apr 6 20:51 cpu
drwxr-xr-x 2 2014 504 4.0K Apr 6 20:51 cuda
-rw-r--r-- 1 2014 504 2.2K Apr 6 20:51 roi_align.py
-rw-r--r-- 1 2014 504 1.8K Apr 6 20:51 setup.py
-rw-r--r-- 1 2014 504 282 Apr 6 20:51 vision.cpp
(anaconda3-2019.07/envs/snake) ➜ roi_align_layer git:(master) ✗ python setup.py build_ext --inplace
running build_ext
copying build/lib.linux-x86_64-3.7/_roi_align.cpython-37m-x86_64-linux-gnu.so ->
(anaconda3-2019.07/envs/snake) ➜ roi_align_layer git:(master) ✗ cd ..
(anaconda3-2019.07/envs/snake) ➜ csrc git:(master) ✗ cd ..
(anaconda3-2019.07/envs/snake) ➜ lib git:(master) ✗ cd ..
anaconda3-2019.07/envs/snak ) ➜ snake git:(master) ✗ python train_net.py --cfg_file configs/sbd_snake.yaml model custom_model train.dataset CocT Traceback (most recent call last):
File "train_net.py", line 54, in <module>
main()
File "train_net.py", line 46, in main
network = make_network(cfg)
File "/ldap_shared/home/s_zyt/inseg/code/snake/lib/networks/make_network.py", line 23, in make_network
return imp.load_source(module, path).get_network(cfg)
File "/ldap_shared/home/s_zyt/.pyenv/versions/anaconda3-2019.07/envs/snake/lib/python3.7/imp.py", line 171, in load_source
module = _load(spec)
File "<frozen importlib._bootstrap>", line 696, in _load
File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 728, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "lib/networks/snake/__init__.py", line 2, in <module>
from .ct_snake import get_network as get_ro
File "lib/networks/snake/ct_snake.py", line 2, in <module>
from .dla import DLASeg
File "lib/networks/snake/dla.py", line 16, in <module>
from lib.networks.dcn_v2 import DCN
File "/ldap_shared/home/s_zyt/inseg/code/snake/lib/networks/dcn_v2.py", line 13, in <module>
from lib.csrc.dcn_v2 import _ext as _backend
ImportError: /ldap_shared/home/s_zyt/inseg/code/snake/lib/csrc/dcn_v2/_ext.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceIN3c108BFloat16EEEPKNS_6detail12TypeMetaDataEv
From the log, it seems my installation is right. The dcn_v2
, extreme_utils
and roi_align_layer
all installed. But I still got this error.
Environment:
- pytorch==1.2.0
- cuda==10.0
from snake.
from snake.
Before re-compiling the code, you need to remove the build
directory under snake/lib/csrc/dcn_v2/
.
from snake.
Related Issues (20)
- Code errors and broken links HOT 1
- Mask map HOT 3
- 更换backbone HOT 4
- 修改loss函数 HOT 1
- 对比实验评估问题 HOT 1
- Cityscapes数据集缺失问题
- Cityscapes数据集缺失问题 HOT 2
- “THC/THC.h”: No such file or directory HOT 5
- dla-34改dla60 HOT 1
- RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED HOT 2
- SBD数据集貌似失效了,请问可以更新一下链接嘛! HOT 1
- ex_loss 和py_loss的含义 HOT 1
- 使用自己制作COCO数据集报错的问题 HOT 1
- 如何能够在目标检测的框上面显示类别 HOT 2
- dance这篇论文在snake的基础上改进,修改了损失函数 HOT 1
- 作者您好,关于如何显示测试结果的分类别mAP? HOT 1
- 请问作者每一次迭代的效果图在代码中是怎么实现的 HOT 1
- 损失曲线问题
- Costum dataset
- windows10,python3.7,vs2022构建失败:dcn_v2,extreme_utils,roi_align_layer
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 snake.