media-smart / vedadet Goto Github PK
View Code? Open in Web Editor NEWA single stage object detection toolbox based on PyTorch
License: Apache License 2.0
vedadet's People
Contributors
Stargazers
Watchers
Forkers
mike112223 xxxhycl2010 zilipeng baodijun wangdeyu nemonameless leeensub z1z9b89 zzh-tju qaz734913414 xrosliang manongdarker acdream007 undercontroller huangwenwenlili huqiang920523 bartoszsambor yawei666 trantorrepository aliushn shiyuan680 gmt710 cv-ip mei-727 zfxu chasemonsteraway c1a1o1 wuyunxiangwyx ruofei7 xiaowenhe wenbank linghai06 waterbearbee julioteleco yingjun-zhang chengliu1995 pustar github2016hdu xwjbupt eothelily wolfworld6 huxwell stetchplane jliangqiu fengxh1989 dev233 peternara ericustc sinianyutian liciciyi qicongsun choi612 kvrooman tapdap dmx666 liuguoyou kuro96 ljdongysu mjs2600 yuxinzou malixiaoguo qwopqwop200 fengj0 zhangjiekui luckyzxy182 darththomas zineos rriyaldhi jie311 suke0 gonepiao c-h-wong smallhedgehogg chengsongyang luca-zanella-dvl xlsean goodgoodstudy92 chaucerg berrlinn itsthanhtung atomeyang rexiome danielschulz shaking54 enqoda alvahan ngfuong shawnlovegame cosmoshua lord-aresyzen tailocbmt dendiv noot2000 bilzard luyz5 sett1ement vokhidovhusan cuongdv1 kmukash deepdriveplvedadet's Issues
How to run a demo on win10 ?
Align faces availability
Is there a provision to align faces detected ?
multi-scale testing
@Media-Smart Thanks for your great work! What parameters should I modify in config/trainval/tinaface.py if I want to complete multi-scale testing? Looking forward to your reply.
About training
When the training is interrupted at epoch70, the effect will drop sharply whether the training is continued at epoch70 or epoch60.
epoch 60:
training from epoch70, the result of epoch 90:
training from epoch60, the result of epoch 90:
May I ask what causes this?
mobilev3 backbone
Hi, thanks for your share the interesting repo.
have you used the mobilev3 as backbone for tinaface?
whether the training strategy should be changed?
pip install -v -e . error
Requirement already satisfied: cython in /home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages (from -r requirements/build.txt (line 1)) (0.29.21) Requirement already satisfied: numpy in /home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages (from -r requirements/build.txt (line 2)) (1.19.4) (vedadet-2) yjq@a504:~/Research_traning/vedadet$ pip install -v -e . Using pip 20.3.3 from /home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip (python 3.7) Non-user install because site-packages writeable Created temporary directory: /tmp/pip-ephem-wheel-cache-3rh0g7c3 Created temporary directory: /tmp/pip-req-tracker-zn8_qdff Initialized build tracking at /tmp/pip-req-tracker-zn8_qdff Created build tracker: /tmp/pip-req-tracker-zn8_qdff Entered build tracker: /tmp/pip-req-tracker-zn8_qdff Created temporary directory: /tmp/pip-install-ovmbn9c9 Obtaining file:///home/yjq/Research_traning/vedadet Added file:///home/yjq/Research_traning/vedadet to build tracker '/tmp/pip-req-tracker-zn8_qdff' Running setup.py (path:/home/yjq/Research_traning/vedadet/setup.py) egg_info for package from file:///home/yjq/Research_traning/vedadet Created temporary directory: /tmp/pip-pip-egg-info-6o1hrl7f Running command python setup.py egg_info running egg_info creating /tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info writing /tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/PKG-INFO writing dependency_links to /tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/dependency_links.txt writing top-level names to /tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/top_level.txt writing manifest file '/tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/SOURCES.txt' reading manifest file '/tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/SOURCES.txt' writing manifest file '/tmp/pip-pip-egg-info-6o1hrl7f/vedadet.egg-info/SOURCES.txt' Source in /home/yjq/Research_traning/vedadet has version 0.1.0, which satisfies requirement vedadet==0.1.0 from file:///home/yjq/Research_traning/vedadet Removed vedadet==0.1.0 from file:///home/yjq/Research_traning/vedadet from build tracker '/tmp/pip-req-tracker-zn8_qdff' Created temporary directory: /tmp/pip-unpack-h44ry_c1 Installing collected packages: vedadet Running setup.py develop for vedadet Running command /home/yjq/miniconda3/envs/vedadet-2/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/yjq/Research_traning/vedadet/setup.py'"'"'; __file__='"'"'/home/yjq/Research_traning/vedadet/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 running develop running egg_info writing vedadet.egg-info/PKG-INFO writing dependency_links to vedadet.egg-info/dependency_links.txt writing top-level names to vedadet.egg-info/top_level.txt reading manifest file 'vedadet.egg-info/SOURCES.txt' writing manifest file 'vedadet.egg-info/SOURCES.txt' running build_ext building 'vedadet.ops.nms.nms_ext' extension gcc -pthread -B /home/yjq/miniconda3/envs/vedadet-2/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/TH -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/yjq/miniconda3/envs/vedadet-2/include/python3.7m -c vedadet/ops/nms/src/nms_ext.cpp -o build/temp.linux-x86_64-3.7/vedadet/ops/nms/src/nms_ext.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_ext -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++ gcc -pthread -B /home/yjq/miniconda3/envs/vedadet-2/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/TH -I/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/yjq/miniconda3/envs/vedadet-2/include/python3.7m -c vedadet/ops/nms/src/cpu/nms_cpu.cpp -o build/temp.linux-x86_64-3.7/vedadet/ops/nms/src/cpu/nms_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_ext -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++ vedadet/ops/nms/src/cpu/nms_cpu.cpp: In function ‘at::Tensor nms_cpu_kernel(const at::Tensor&, float)’: vedadet/ops/nms/src/cpu/nms_cpu.cpp:29:50: error: expected primary-expression before ‘>’ token auto suppressed = suppressed_t.data_ptr<uint8_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:29:52: error: expected primary-expression before ‘)’ token auto suppressed = suppressed_t.data_ptr<uint8_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:30:38: error: expected primary-expression before ‘>’ token auto keep = keep_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:30:40: error: expected primary-expression before ‘)’ token auto keep = keep_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:31:40: error: expected primary-expression before ‘>’ token auto order = order_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:31:42: error: expected primary-expression before ‘)’ token auto order = order_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:32:35: error: expected primary-expression before ‘>’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:32:37: error: expected primary-expression before ‘)’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:33:35: error: expected primary-expression before ‘>’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:33:37: error: expected primary-expression before ‘)’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:34:35: error: expected primary-expression before ‘>’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:34:37: error: expected primary-expression before ‘)’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:35:35: error: expected primary-expression before ‘>’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:35:37: error: expected primary-expression before ‘)’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:36:41: error: expected primary-expression before ‘>’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:36:43: error: expected primary-expression before ‘)’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp: In function ‘at::Tensor soft_nms_cpu_kernel(const at::Tensor&, float, unsigned char, float, float)’: vedadet/ops/nms/src/cpu/nms_cpu.cpp:95:35: error: expected primary-expression before ‘>’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:95:37: error: expected primary-expression before ‘)’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:96:35: error: expected primary-expression before ‘>’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:96:37: error: expected primary-expression before ‘)’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:97:35: error: expected primary-expression before ‘>’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:97:37: error: expected primary-expression before ‘)’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:98:35: error: expected primary-expression before ‘>’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:98:37: error: expected primary-expression before ‘)’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:99:43: error: expected primary-expression before ‘>’ token auto scores = scores_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:99:45: error: expected primary-expression before ‘)’ token auto scores = scores_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:100:41: error: expected primary-expression before ‘>’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:100:43: error: expected primary-expression before ‘)’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:104:39: error: expected primary-expression before ‘>’ token auto inds = inds_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:104:41: error: expected primary-expression before ‘)’ token auto inds = inds_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp: In function ‘std::vector<std::vector<int> > nms_match_cpu_kernel(const at::Tensor&, float)’: vedadet/ops/nms/src/cpu/nms_cpu.cpp:239:50: error: expected primary-expression before ‘>’ token auto suppressed = suppressed_t.data_ptr<uint8_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:239:52: error: expected primary-expression before ‘)’ token auto suppressed = suppressed_t.data_ptr<uint8_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:240:40: error: expected primary-expression before ‘>’ token auto order = order_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:240:42: error: expected primary-expression before ‘)’ token auto order = order_t.data_ptr<int64_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:241:35: error: expected primary-expression before ‘>’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:241:37: error: expected primary-expression before ‘)’ token auto x1 = x1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:242:35: error: expected primary-expression before ‘>’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:242:37: error: expected primary-expression before ‘)’ token auto y1 = y1_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:243:35: error: expected primary-expression before ‘>’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:243:37: error: expected primary-expression before ‘)’ token auto x2 = x2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:244:35: error: expected primary-expression before ‘>’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:244:37: error: expected primary-expression before ‘)’ token auto y2 = y2_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:245:41: error: expected primary-expression before ‘>’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ vedadet/ops/nms/src/cpu/nms_cpu.cpp:245:43: error: expected primary-expression before ‘)’ token auto areas = areas_t.data_ptr<scalar_t>(); ^ error: command 'gcc' failed with exit status 1 ERROR: Command errored out with exit status 1: /home/yjq/miniconda3/envs/vedadet-2/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/yjq/Research_traning/vedadet/setup.py'"'"'; __file__='"'"'/home/yjq/Research_traning/vedadet/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. Exception information: Traceback (most recent call last): File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/cli/base_command.py", line 224, in _main status = self.run(options, args) File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/cli/req_command.py", line 180, in wrapper return func(self, options, args) File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/commands/install.py", line 403, in run pycompile=options.compile, File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/req/__init__.py", line 90, in install_given_reqs pycompile=pycompile, File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/req/req_install.py", line 802, in install unpacked_source_directory=self.unpacked_source_directory, File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/operations/install/editable_legacy.py", line 51, in install_editable cwd=unpacked_source_directory, File "/home/yjq/miniconda3/envs/vedadet-2/lib/python3.7/site-packages/pip/_internal/utils/subprocess.py", line 240, in call_subprocess raise InstallationError(exc_msg) pip._internal.exceptions.InstallationError: Command errored out with exit status 1: /home/yjq/miniconda3/envs/vedadet-2/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/home/yjq/Research_traning/vedadet/setup.py'"'"'; __file__='"'"'/home/yjq/Research_traning/vedadet/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. Removed build tracker: '/tmp/pip-req-tracker-zn8_qdff'
cant load the weighs file I trained
I use tinaface resnet50 you pretrained to train my self data. I got three pth output (optimizer,meta,weights) ,then I use the weights.pth to be loaded by the inference but an error occured : failed reading zip archive.. which pth file should be loaded to inference?
Face detection
Thank you for your hard work，
before run infer.py,it need us modify some configuration accordingly in the config file like configs/infer/retinanet/retinanet.py,What are these parameters？just change the num_classes ande classes_names?Looking forward to your reply。
ImportError: cannot import name 'deform_conv_ext'
Greatly thank for your sharing.
when I run the command:
tools/dist_trainval.sh configs/trainval/tinaface/tinaface.py "0,1,2,3"
I met this problem:
ImportError: cannot import name 'deform_conv_ext'
Maybe this cause by dcn, Would you mind giving some suggestions for me?
Thx.
is there a way to tackle more than one image ?
Hi is there a way to tackle more than one image ?
i set the path as an image directory, it tackles only one and says that others are error ?
command line
CUDA_VISIBLE_DEVICES="0" python tools/infer.py configs/infer/tinaface/tinaface.py /mnt/disk6T0/test/img/*
output
infer.py: error: unrecognized arguments: /mnt/disk6T0/test/img/2.jpeg
could you provide baidu download for widerface model ?
thx
TinaFace - validation mAP 0.825 only
cd ${vedadet_root} python configs/trainval/tinaface/test_widerface.py configs/trainval/tinaface/tinaface.py tinaface_r50_fpn_widerface.pth
I have run the TinaFace example on WiderFaces validation set getting only 0.825 mAP (I was expecting smth north of 0.9).
Is this the expected val score, or rather I must have messed up with dataset setup?
Is there any chance you can share setup you use to adapt WiderFaces to your pipeline?
tinaface_r50_fpn_widerface.pth mAP仅0.628
tinaface_r50_fpn_widerface.pth测试，按照Issues #25的过程做了一遍，还是下面的结果，做了filter_widerface_val.py以后感觉xml没什么变化?
+-------+-------+---------+--------+-------+
| class | gts | dets | recall | ap |
+-------+-------+---------+--------+-------+
| face | 31957 | 8420592 | 0.837 | 0.628 |
+-------+-------+---------+--------+-------+
| mAP | | | | 0.628 |
+-------+-------+---------+--------+-------+
how to evaluate the performance on test set?
Hi!
thanks for sharing the code, but i do not understand how to evaluate on test set as there is no '.txt' file in test set? how should i modify the tinaface.py？ thank you so much!!
cuda version
Is cuda version 10.1 is OK? I am difficult to run this program. Is it because of the version?
Question on TinaFace training setting?
Hi @hxcai , thanks for sharing the impressive work. I have read the TinaFace paper and been puzzled by the training setting in the paper. The lr schedule and lr rate seems very complex and differs a lot from the official RetinaNet. Is this training setting a careful tunning result of the experiments or being inspired by other work. Could you reveal the motivation behind that? Thank you!
您好，我自己想训练自己的数据集，但是一直加载有问题，请问一下我不想加载使用resnet50的预训练模型，我该更改什么地方呢，谢谢您
FileNotFoundError: [Errno 2] No such file or directory: 'data/COCO2017/annotations/instances_train2017.json'
when I run this command
CUDA_VISIBLE_DEVICES="0" python tools/trainval.py configs/trainval/retinanet/retinanet.py
The implementation of Box Voting
Hi, it seems that box voting code is not implemented in this repo. Could you give some details on how you perform box voting over 10,000 * (2(flip) * 4(500,800,1100,1400,1700) * 4(shift)) boxes at most with box voting? It seems that batched NMS(lb-nms in this codebase) is not fit for box voting. Thanks!
run speed?
Hello! I found the speed was slow almost near 1.4 second per image When I tried the eval code . Is it normal? My environment is v100.
Maybe anchor-free version with GFLV2
Hi~
You can try anchor-free version with GFocalV2，maybe the performance can be further boosted without extra cost~
怎么可视化loss的收敛过程？
How about TinaFace performance?
How about TinaFace performance?
Spurious large boxes with TinaFace
Hello, I run the inferece script using the TinaFace model using the pretrained weights and I get some spurious large boxes in several examples. For example for this image the resulted boxes were as follows.
Is there any indication about what is wrong, is this expected for some cases, or is anything that can be changed in the config except the inference threshold?
不好用
项目封装的太好了，要看好久才看明白，想尝试改一个带landmark的轻量级tinaface，期待多写些说明文档
RuntimeError: CUDA error: no kernel image is available for execution on the device
python configs/trainval/tinaface/test_widerface.py configs/trainval/tinaface/tinaface.py data/tinaface_r50_fpn_widerface.pth
loading annotations into memory... Done (t=0.00s) creating index... index created! [ ] 0/55, elapsed: 0s, ETA:Traceback (most recent call last): File "configs/trainval/tinaface/test_widerface.py", line 101, in <module> main() File "configs/trainval/tinaface/test_widerface.py", line 96, in main results = test(engine, data_loader, args.outdir) File "configs/trainval/tinaface/test_widerface.py", line 77, in test result = engine(data)[0] File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedacore/parallel/data_parallel.py", line 30, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/engines/val_engine.py", line 15, in forward return self.forward_impl(**data) File "/home/yjq/Research_traning/vedadet/vedadet/engines/val_engine.py", line 18, in forward_impl dets = self.infer(img, img_metas) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 115, in infer return self._simple_infer(img[0], img_metas[0]) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 57, in _simple_infer dets = self._get_raw_dets(img, img_metas) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 36, in _get_raw_dets feats = self.extract_feats(img) File "/home/yjq/Research_traning/vedadet/vedadet/engines/infer_engine.py", line 24, in extract_feats feats = self.model(img, train=False) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/models/detectors/single_stage_detector.py", line 48, in forward feats = self.forward_impl(x) File "/home/yjq/Research_traning/vedadet/vedadet/models/detectors/single_stage_detector.py", line 35, in forward_impl feats = self.backbone(x) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/Research_traning/vedadet/vedadet/models/backbones/resnet.py", line 624, in forward x = self.norm1(x) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/modules/normalization.py", line 245, in forward return F.group_norm( File "/home/yjq/miniconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/functional.py", line 2111, in group_norm return torch.group_norm(input, num_groups, weight, bias, eps, RuntimeError: CUDA error: no kernel image is available for execution on the device
Pretrained
I could not find the pretrained model. Where can I download it?
Too much training time, Any faster training schedule?
Hi, Thanks for this great work. However, the training time is quite long, (about 60h on 6 V100s) which is hard for us to verify other ideas on this code. Have you ever tried some shorter schedule? and how about the performance?
The model and loaded state dict do not match exactly
你好，请问运行CUDA_VISIBLE_DEVICES="0" python tools/trainval.py configs/trainval/retinanet/retinanet.py时出现以下信息之后就一直不动了，是什么原因，找了半天没找出原因
`
loading annotations into memory...
Done (t=0.02s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
2020-12-19 19:12:36,718 - vedadet - INFO - Loading weights from torchvision://resnet50
2020-12-19 19:12:36,919 - vedadet - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: backbone.fc.weight, backbone.fc.bias
missing keys in source state_dict: neck.lateral_convs.0.conv.weight, neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.weight, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.weight, neck.lateral_convs.2.conv.bias, neck.fpn_convs.0.conv.weight, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.weight, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.weight, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.weight, neck.fpn_convs.3.conv.bias, neck.fpn_convs.4.conv.weight, neck.fpn_convs.4.conv.bias, bbox_head.cls_convs.0.conv.weight, bbox_head.cls_convs.0.conv.bias, bbox_head.cls_convs.1.conv.weight, bbox_head.cls_convs.1.conv.bias, bbox_head.cls_convs.2.conv.weight, bbox_head.cls_convs.2.conv.bias, bbox_head.cls_convs.3.conv.weight, bbox_head.cls_convs.3.conv.bias, bbox_head.reg_convs.0.conv.weight, bbox_head.reg_convs.0.conv.bias, bbox_head.reg_convs.1.conv.weight, bbox_head.reg_convs.1.conv.bias, bbox_head.reg_convs.2.conv.weight, bbox_head.reg_convs.2.conv.bias, bbox_head.reg_convs.3.conv.weight, bbox_head.reg_convs.3.conv.bias, bbox_head.retina_cls.weight, bbox_head.retina_cls.bias, bbox_head.retina_reg.weight, bbox_head.retina_reg.bias
2020-12-19 19:12:37,126 - vedadet - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: backbone.fc.weight, backbone.fc.bias
missing keys in source state_dict: neck.lateral_convs.0.conv.weight, neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.weight, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.weight, neck.lateral_convs.2.conv.bias, neck.fpn_convs.0.conv.weight, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.weight, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.weight, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.weight, neck.fpn_convs.3.conv.bias, neck.fpn_convs.4.conv.weight, neck.fpn_convs.4.conv.bias, bbox_head.cls_convs.0.conv.weight, bbox_head.cls_convs.0.conv.bias, bbox_head.cls_convs.1.conv.weight, bbox_head.cls_convs.1.conv.bias, bbox_head.cls_convs.2.conv.weight, bbox_head.cls_convs.2.conv.bias, bbox_head.cls_convs.3.conv.weight, bbox_head.cls_convs.3.conv.bias, bbox_head.reg_convs.0.conv.weight, bbox_head.reg_convs.0.conv.bias, bbox_head.reg_convs.1.conv.weight, bbox_head.reg_convs.1.conv.bias, bbox_head.reg_convs.2.conv.weight, bbox_head.reg_convs.2.conv.bias, bbox_head.reg_convs.3.conv.weight, bbox_head.reg_convs.3.conv.bias, bbox_head.retina_cls.weight, bbox_head.retina_cls.bias, bbox_head.retina_reg.weight, bbox_head.retina_reg.bias
`
Run from a pretrained model.
Hey I'm getting this error when I try to run the tinaface.py file with the pretrained model.Can you help me out?
Traceback (most recent call last):
File "tools/infer.py", line 93, in
main()
File "tools/infer.py", line 75, in main
engine, data_pipeline, device = prepare(cfg)
File "tools/infer.py", line 31, in prepare
load_weights(engine.model, cfg.weights.filepath)
File "/content/vedadet/configs/vedadet/vedacore/misc/checkpoint.py", line 238, in load_weights
state_dict = _load_checkpoint(filepath, map_location)
File "/content/vedadet/configs/vedadet/vedacore/misc/checkpoint.py", line 135, in _load_checkpoint
raise IOError(f'{filepath} is not a file')
OSError: your/weight/file/path is not a file
"error in deformable_im2col: no kernel image is available for execution on the device" with different GPU
thanks! I build the environment step by step, but when executed the training or inference code on V100, "error in deformable_im2col: no kernel image is available for execution on the device". when running on RTX8000, there is no error.
Inference using multigpu on lots of images.
The tool/infer.py is designed to process only an image at a time with one gpu. What if there are lots of images to infer? Is there any tutorials or small code snipets to implement large-scale inference?
Failed to convert TinaFace into ONNX format
environment
- python 3.7.9
- torch 1.6.0
- torchvision 0.7.0
My script
The config file tinaface.py hasn't been modified
cfg = Config.fromfile("configs/trainval/tinaface/tinaface.py")
device = 'cpu'
model = build_detector(cfg.model)
load_weights(model,"tinaface_r50_fpn_widerface.pth")
model.to(device)
model.forward = model.forward_impl
shape = [3, 800, 1344]
dummy_input = torch.randn(1, *shape)
torch2onnx(model, dummy_input, "test.onnx", dynamic_shape=False,
opset_version=9,
do_constant_folding=False,
verbose=False)Error Log
~/miniconda3/envs/modelci/bin/python ~/github/ML-Model-CI/example/notebook/repo/test2.py
Traceback (most recent call last):
File "~/github/ML-Model-CI/example/notebook/repo/test2.py", line 33, in <module>
main()
File "~/github/ML-Model-CI/example/notebook/repo/test2.py", line 28, in main
verbose=False)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/volksdep/converters/torch2onnx.py", line 40, in torch2onnx
output = model(dummy_input)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "~/github/ML-Model-CI/example/notebook/repo/vedadet/models/detectors/single_stage_detector.py", line 35, in forward_impl
feats = self.backbone(x)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "~/github/ML-Model-CI/example/notebook/repo/vedadet/models/backbones/resnet.py", line 630, in forward
x = res_layer(x)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/container.py", line 117, in forward
input = module(input)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "~/github/ML-Model-CI/example/notebook/repo/vedadet/models/backbones/resnet.py", line 297, in forward
out = _inner_forward(x)
File "~/github/ML-Model-CI/example/notebook/repo/vedadet/models/backbones/resnet.py", line 274, in _inner_forward
out = self.conv2(out)
File "~/miniconda3/envs/modelci/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "~repo/vedadet/ops/dcn/deform_conv.py", line 302, in forward
self.dilation, self.groups, self.deformable_groups)
File "~/repo/vedadet/ops/dcn/deform_conv.py", line 46, in forward
raise NotImplementedError
NotImplementedError
Process finished with exit code 1
Update eval_tools link in TinaFace Readme
The link for eval_tools in the Readme.md file of vedadet/configs/trainval/tinaface/ has been changed to this link.
Please update the same.
Segmentation fault
When I am doing test and inference, there are always Segmentation fault come out and interrupt the process.
I can't figure out where is wrong with the memory allocation, please have a look with the Backtrace.
(vedadet) [root@localhost vedadet]# CUDA_VISIBLE_DEVICES="1,2" python tools/infer.py configs/infer/tinaface/tinaface.py t1.jpg
/data/anaconda3/envs/vedadet/lib/python3.8/site-packages/torch/nn/functional.py:3060: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn("Default upsampling behavior when mode={} is changed "
*** Error in `python': free(): invalid pointer: 0x000055b33065d600 ***
======= Backtrace: =========
/lib64/libc.so.6(+0x81299)[0x7f8f43d7f299]
/usr/local/cuda-11.0/lib64/libcublasLt.so.11(free_gemm_select+0x4d)[0x7f8f03b5ea3d]
/data/anaconda3/envs/vedadet/lib/python3.8/site-packages/torch/lib/../../../../libcublas.so.11(cublasDestroy_v2+0x165)[0x7f8f0e991af5]
/data/anaconda3/envs/vedadet/lib/python3.8/site-packages/torch/lib/libtorch_cuda.so(+0x25a4345d)[0x7f8ea992f45d]
/data/anaconda3/envs/vedadet/lib/python3.8/site-packages/torch/lib/libtorch_cuda.so(+0x25a43561)[0x7f8ea992f561]
/lib64/libc.so.6(+0x39ce9)[0x7f8f43d37ce9]
/lib64/libc.so.6(+0x39d37)[0x7f8f43d37d37]
/lib64/libc.so.6(__libc_start_main+0xfc)[0x7f8f43d2055c]
python(+0x1dee93)[0x55b2d9117e93]
======= Memory map: ========
200000000-200200000 ---p 00000000 00:00 0
200200000-200400000 rw-s 00000000 00:05 19850 /dev/nvidiactl
200400000-202400000 rw-s 00000000 00:05 19850 /dev/nvidiactl
202400000-205400000 rw-s 00000000 00:05 19850 /dev/nvidiactl
205400000-206000000 ---p 00000000 00:00 0
206000000-206200000 rw-s 00000000 00:05 19850 /dev/nvidiactl
206200000-206400000 rw-s 00000000 00:05 19850 /dev/nvidiactl
206400000-206600000 rw-s 206400000 00:05 63275 /dev/nvidia-uvm
206600000-206800000 rw-s 00000000 00:05 19850 /dev/nvidiactl
206800000-206a00000 ---p 00000000 00:00 0
206a00000-206c00000 rw-s 00000000 00:05 19850 /dev/nvidiactl
206c00000-400200000 ---p 00000000 00:00 0
10000000000-10104000000 ---p 00000000 00:00 0
55b2d8f39000-55b2d8f98000 r--p 00000000 fd:04 4026537124 /data/anaconda3/envs/vedadet/bin/python3.8
55b2d8f98000-55b2d9189000 r-xp 0005f000 fd:04 4026537124 /data/anaconda3/envs/vedadet/bin/python3.8
55b2d9189000-55b2d926f000 r--p 00250000 fd:04 4026537124 /data/anaconda3/envs/vedadet/bin/python3.8
55b2d9270000-55b2d9275000 r--p 00336000 fd:04 4026537124 /data/anaconda3/envs/vedadet/bin/python3.8
55b2d9275000-55b2d92ad000 rw-p 0033b000 fd:04 4026537124 /data/anaconda3/envs/vedadet/bin/python3.8
55b2d92ad000-55b2d92cd000 rw-p 00000000 00:00 0
55b2d9f58000-55b331409000 rw-p 00000000 00:00 0 [heap]
7f8c54000000-7f8c54021000 rw-p 00000000 00:00 0
7f8c54021000-7f8c58000000 ---p 00000000 00:00 0
7f8c5c000000-7f8c9b200000 ---p 00000000 00:00 0
7f8c9b200000-7f8c9b400000 rw-s 00000000 00:04 44358018 /dev/zero (deleted)
7f8c9b400000-7f8c9c000000 ---p 00000000 00:00 0
7f8c9c000000-7f8c9c021000 rw-p 00000000 00:00 0
7f8c9c021000-7f8ca0000000 ---p 00000000 00:00 0
7f8ca0000000-7f8ca0021000 rw-p 00000000 00:00 0
7f8ca0021000-7f8ca4000000 ---p 00000000 00:00 0
7f8ca4000000-7f8ca4021000 rw-p 00000000 00:00 0
7f8ca4021000-7f8ca8000000 ---p 00000000 00:00 0
7f8caaffe000-7f8caafff000 ---p 00000000 00:00 0
7f8caafff000-7f8cab7ff000 rw-p 00000000 00:00 0
7f8cab7ff000-7f8cab800000 ---p 00000000 00:00 0
7f8cab800000-7f8cac000000 rw-p 00000000 00:00 0
7f8cac000000-7f8cac021000 rw-p 00000000 00:00 0
7f8cac021000-7f8cb0000000 ---p 00000000 00:00 0
7f8cb0000000-7f8cb0021000 rw-p 00000000 00:00 0
7f8cb0021000-7f8cb4000000 ---p 00000000 00:00 0
7f8cb4000000-7f8cb4021000 rw-p 00000000 00:00 0
7f8cb4021000-7f8cb8000000 ---p 00000000 00:00 0
7f8cb8000000-7f8cb8021000 rw-p 00000000 00:00 0
7f8cb8021000-7f8cbc000000 ---p 00000000 00:00 0
7f8cbc000000-7f8cbc021000 rw-p 00000000 00:00 0
7f8cbc021000-7f8cc0000000 ---p 00000000 00:00 0
7f8cc0000000-7f8cc0021000 rw-p 00000000 00:00 0
7f8cc0021000-7f8cc4000000 ---p 00000000 00:00 0
7f8cc4000000-7f8cc4021000 rw-p 00000000 00:00 0
7f8cc4021000-7f8cc8000000 ---p 00000000 00:00 0
7f8cc87f9000-7f8cc87fa000 ---p 00000000 00:00 0
7f8cc87fa000-7f8cc8ffa000 rw-p 00000000 00:00 0
7f8cc8ffa000-7f8cc8ffb000 ---p 00000000 00:00 0
7f8cc8ffb000-7f8cc97fb000 rw-p 00000000 00:00 0
7f8cc97fb000-7f8cc97fc000 ---p 00000000 00:00 0
7f8cc97fc000-7f8cc9ffc000 rw-p 00000000 00:00 0
7f8cc9ffc000-7f8cc9ffd000 ---p 00000000 00:00 0
7f8cc9ffd000-7f8cca7fd000 rw-p 00000000 00:00 0
7f8cca7fd000-7f8cca7fe000 ---p 00000000 00:00 0
7f8cca7fe000-7f8ccaffe000 rw-p 00000000 00:00 0
7f8ccaffe000-7f8ccafff000 ---p 00000000 00:00 0
7f8ccafff000-7f8ccb7ff000 rw-p 00000000 00:00 0
7f8ccb7ff000-7f8ccb800000 ---p 00000000 00:00 0
7f8ccb800000-7f8ccc000000 rw-p 00000000 00:00 0
7f8ccc000000-7f8ccc021000 rw-p 00000000 00:00 0
7f8ccc021000-7f8cd0000000 ---p 00000000 00:00 0
7f8cd0000000-7f8cd0021000 rw-p 00000000 00:00 0
7f8cd0021000-7f8cd4000000 ---p 00000000 00:00 0
7f8cd4000000-7f8cd4021000 rw-p 00000000 00:00 0
7f8cd4021000-7f8cd8000000 ---p 00000000 00:00 0
7f8cd8000000-7f8cd8021000 rw-p 00000000 00:00 0
7f8cd8021000-7f8cdc000000 ---p 00000000 00:00 0
7f8cdc000000-7f8cdc021000 rw-p 00000000 00:00 0
7f8cdc021000-7f8ce0000000 ---p 00000000 00:00 0
7f8ce0000000-7f8ce0021000 rw-p 00000000 00:00 0
7f8ce0021000-7f8ce4000000 ---p 00000000 00:00 0
7f8ce4000000-7f8ce4021000 rw-p 00000000 00:00 0
7f8ce4021000-7f8ce8000000 ---p 00000000 00:00 0
7f8ce8000000-7f8ce8021000 rw-p 00000000 00:00 0
7f8ce8021000-7f8cec000000 ---p 00000000 00:00 0
7f8cec7f9000-7f8cec7fa000 ---p 00000000 00:00 0
7f8cec7fa000-7f8cecffa000 rw-p 00000000 00:00 0
7f8cecffa000-7f8cecffb000 ---p 00000000 00:00 0
7f8cecffb000-7f8ced7fb000 rw-p 00000000 00:00 0
7f8ced7fb000-7f8ced7fc000 ---p 00000000 00:00 0
7f8ced7fc000-7f8cedffc000 rw-p 00000000 00:00 0
7f8cedffc000-7f8cedffd000 ---p 00000000 00:00 0
7f8cedffd000-7f8cee7fd000 rw-p 00000000 00:00 0
7f8cee7fd000-7f8cee7fe000 ---p 00000000 00:00 0
7f8cee7fe000-7f8ceeffe000 rw-p 00000000 00:00 0
7f8ceeffe000-7f8ceefff000 ---p 00000000 00:00 0
7f8ceefff000-7f8cef7ff000 rw-p 00000000 00:00 0
7f8cef7ff000-7f8cef800000 ---p 00000000 00:00 0
7f8cef800000-7f8cf0000000 rw-p 00000000 00:00 0
7f8cf0000000-7f8cf0021000 rw-p 00000000 00:00 0
7f8cf0021000-7f8cf4000000 ---p 00000000 00:00 0
7f8cf4000000-7f8cf4021000 rw-p 00000000 00:00 0
7f8cf4021000-7f8cf8000000 ---p 00000000 00:00 0
7f8cf8000000-7f8cf8021000 rw-p 00000000 00:00 0
7f8cf8021000-7f8cfc000000 ---p 00000000 00:00 0
7f8cfc000000-7f8cfc021000 rw-p 00000000 00:00 0
7f8cfc021000-7f8d00000000 ---p 00000000 00:00 0
7f8d00000000-7f8d00021000 rw-p 00000000 00:00 0
7f8d00021000-7f8d04000000 ---p 00000000 00:00 0
7f8d04000000-7f8d04021000 rw-p 00000000 00:00 0
7f8d04021000-7f8d08000000 ---p 00000000 00:00 0
7f8d08000000-7f8d08021000 rw-p 00000000 00:00 0
7f8d08021000-7f8d0c000000 ---p 00000000 00:00 0
7f8d0c000000-7f8d0c021000 rw-p 00000000 00:00 0
7f8d0c021000-7f8d10000000 ---p 00000000 00:00 0
7f8d10000000-7f8d10021000 rw-p 00000000 00:00 0
7f8d10021000-7f8d14000000 ---p 00000000 00:00 0
7f8d14000000-7f8d14021000 rw-p 00000000 00:00 0
7f8d14021000-7f8d18000000 ---p 00000000 00:00 0
7f8d18000000-7f8d18021000 rw-p 00000000 00:00 0
7f8d18021000-7f8d1c000000 ---p 00000000 00:00 0
7f8d1c7f9000-7f8d1c7fa000 ---p 00000000 00:00 0
7f8d1c7fa000-7f8d1cffa000 rw-p 00000000 00:00 0
7f8d1cffa000-7f8d1cffb000 ---p 00000000 00:00 0
7f8d1cffb000-7f8d1d7fb000 rw-p 00000000 00:00 0
7f8d1d7fb000-7f8d1d7fc000 ---p 00000000 00:00 0
7f8d1d7fc000-7f8d1dffc000 rw-p 00000000 00:00 0
7f8d1dffc000-7f8d1dffd000 ---p 00000000 00:00 0
7f8d1dffd000-7f8d1e7fd000 rw-p 00000000 00:00 0
7f8d1e7fd000-7f8d1e7fe000 ---p 00000000 00:00 0
7f8d1e7fe000-7f8d1effe000 rw-p 00000000 00:00 0
7f8d1effe000-7f8d1efff000 ---p 00000000 00:00 0
7f8d1efff000-7f8d1f7ff000 rw-p 00000000 00:00 0
7f8d1f7ff000-7f8d1f800000 ---p 00000000 00:00 0
7f8d1f800000-7f8d20000000 rw-p 00000000 00:00 0
7f8d20000000-7f8d20021000 rw-p 00000000 00:00 0
7f8d20021000-7f8d24000000 ---p 00000000 00:00 0
7f8d24000000-7f8d24021000 rw-p 00000000 00:00 0
7f8d24021000-7f8d28000000 ---p 00000000 00:00 0
7f8d28000000-7f8d28021000 rw-p 00000000 00:00 0
7f8d28021000-7f8d2c000000 ---p 00000000 00:00 0
7f8d2c000000-7f8d2c021000 rw-p 00000000 00:00 0
7f8d2c021000-7f8d30000000 ---p 00000000 00:00 0
7f8d30000000-7f8d30021000 rw-p 00000000 00:00 0
7f8d30021000-7f8d34000000 ---p 00000000 00:00 0
7f8d34000000-7f8d34021000 rw-p 00000000 00:00 0
7f8d34021000-7f8d38000000 ---p 00000000 00:00 0
7f8d38000000-7f8d38021000 rw-p 00000000 00:00 0
7f8d38021000-7f8d3c000000 ---p 00000000 00:00 0
7f8d3c000000-7f8d3c021000 rw-p 00000000 00:00 0
7f8d3c021000-7f8d40000000 ---p 00000000 00:00 0
7f8d40000000-7f8d40021000 rw-p 00000000 00:00 0
7f8d40021000-7f8d44000000 ---p 00000000 00:00 0
7f8d44000000-7f8d44021000 rw-p 00000000 00:00 0
7f8d44021000-7f8d48000000 ---p 00000000 00:00 0
7f8d48000000-7f8d57000000 ---p 00000000 00:00 0
7f8d57000000-7f8d57200000 rw-s 00000000 00:04 44358017 /dev/zero (deleted)
7f8d57200000-7f8d62400000 ---p 00000000 00:00 0
7f8d62400000-7f8d62600000 rw-s 00000000 00:04 44358012 /dev/zero (deleted)
7f8d62600000-7f8d62800000 rw-s 00000000 00:05 19850 /dev/nvidiactl
7f8d62800000-7f8d62a00000 rw-s 00000000 00:04 44358013 /dev/zero (deleted)
7f8d62a00000-7f8d62e00000 ---p 00000000 00:00 0
7f8d62e00000-7f8d63000000 rw-s 00000000 00:05 19850 /dev/nvidiactl
7f8d63000000-7f8d63200000 rw-s 00000000 00:04 44358015 /dev/zero (deleted)
7f8d63200000-7f8d634d6000 rw-s 00000000 00:05 19850 /dev/nvidiactl
7f8d634d6000-7f8d64000000 ---p 00000000 00:00 0
7f8d64000000-7f8d64021000 rw-p 00000000 00:00 0
7f8d64021000-7f8d68000000 ---p 00000000 00:00 0
7f8d686a7000-7f8d686a8000 ---p 00000000 00:00 0
7f8d686a8000-7f8d68ea8000 rw-p 00000000 00:00 0
7f8d68ea8000-7f8d68ea9000 ---p 00000000 00:00 0
7f8d68ea9000-7f8d696a9000 rw-p 00000000 00:00 0
7f8d696a9000-7f8d696aa000 ---p 00000000 00:00 0
7f8d696aa000-7f8d69eaa000 rw-p 00000000 00:00 0
7f8d69eaa000-7f8d6a0aa000 rw-s 00000000 00:04 44358014 /dev/zero (deleted)
7f8d6a0aa000-7f8d6a0ab000 ---p 00000000 00:00 0
7f8d6a0ab000-7f8d6a8ab000 rw-p 00000000 00:00 0
7f8d6a8ab000-7f8d6a8ac000 ---p 00000000 00:00 0
7f8d6a8ac000-7f8d6b0ac000 rw-p 00000000 00:00 0
7f8d6b7f7000-7f8d6b7f8000 ---p 00000000 00:00 0
7f8d6b7f8000-7f8d6bff8000 rw-p 00000000 00:00 0
7f8d6bff8000-7f8d6bff9000 ---p 00000000 00:00 0
7f8d6bff9000-7f8d6c7f9000 rw-p 00000000 00:00 0
7f8d6c7f9000-7f8d6c7fa000 ---p 00000000 00:00 0
7f8d6c7fa000-7f8d6cffa000 rw-p 00000000 00:00 0
7f8d6cffa000-7f8d6cffb000 ---p 00000000 00:00 0
7f8d6cffb000-7f8d6d7fb000 rw-p 00000000 00:00 0
7f8d6d7fb000-7f8d6d7fc000 ---p 00000000 00:00 0
7f8d6d7fc000-7f8d6dffc000 rw-p 00000000 00:00 0
7f8d6dffc000-7f8d6dffd000 ---p 00000000 00:00 0
7f8d6dffd000-7f8d6e7fd000 rw-p 00000000 00:00 0
7f8d6e7fd000-7f8d6e7fe000 ---p 00000000 00:00 0
7f8d6e7fe000-7f8d6effe000 rw-p 00000000 00:00 0
7f8d6effe000-7f8d6efff000 ---p 00000000 00:00 0
7f8d6efff000-7f8d6f7ff000 rw-p 00000000 00:00 0
7f8d6f7ff000-7f8d6f800000 ---p 00000000 00:00 0
7f8d6f800000-7f8d70000000 rw-p 00000000 00:00 0
7f8d70000000-7f8d70021000 rw-p 00000000 00:00 0
7f8d70021000-7f8d74000000 ---p 00000000 00:00 0
7f8d74000000-7f8d74021000 rw-p 00000000 00:00 0
7f8d74021000-7f8d78000000 ---p 00000000 00:00 0
7f8d78000000-7f8d78021000 rw-p 00000000 00:00 0
7f8d78021000-7f8d7c000000 ---p 00000000 00:00 0
7f8d7c000000-7f8d7c021000 rw-p 00000000 00:00 0
7f8d7c021000-7f8d80000000 ---p 00000000 00:00 0
7f8d80000000-7f8d80021000 rw-p 00000000 00:00 0
7f8d80021000-7f8d84000000 ---p 00000000 00:00 0
7f8d84000000-7f8d84021000 rw-p 00000000 00:00 0
7f8d84021000-7f8d88000000 ---p 00000000 00:00 0
7f8d88000000-7f8d88021000 rw-p 00000000 00:00 0
7f8d88021000-7f8d8c000000 ---p 00000000 00:00 0
7f8d8c000000-7f8d8c021000 rw-p 00000000 00:00 0
7f8d8c021000-7f8d90000000 ---p 00000000 00:00 0
7f8d90000000-7f8d90021000 rw-p 00000000 00:00 0
7f8d90021000-7f8d94000000 ---p 00000000 00:00 0
7f8d947f6000-7f8d947f7000 ---p 00000000 00:00 0
7f8d947f7000-7f8d94ff7000 rw-p 00000000 00:00 0
7f8d94ff7000-7f8d94ff8000 ---p 00000000 00:00 0
7f8d94ff8000-7f8d957f8000 rw-p 00000000 00:00 0
7f8d957f8000-7f8d957f9000 ---p 00000000 00:00 0
7f8d957f9000-7f8d95ff9000 rw-p 00000000 00:00 0
7f8d95ff9000-7f8d95ffa000 ---p 00000000 00:00 0
7f8d95ffa000-7f8d967fa000 rw-p 00000000 00:00 0
7f8d967fa000-7f8d967fb000 ---p 00000000 00:00 0
7f8d967fb000-7f8d96ffc000 rw-p 00000000 00:00 0
7f8d96ffc000-7f8d96ffd000 ---p 00000000 00:00 0
7f8d96ffd000-7f8d977fe000 rw-p 00000000 00:00 0
7f8d977fe000-7f8d977ff000 ---p 00000000 00:00 0
7f8d977ff000-7f8d98000000 rw-p 00000000 00:00 0
7f8d98000000-7f8d98021000 rw-p 00000000 00:00 0
7f8d98021000-7f8d9c000000 ---p 00000000 00:00 0
7f8d9c000000-7f8d9c021000 rw-p 00000000 00:00 0
7f8d9c021000-7f8da0000000 ---p 00000000 00:00 0
7f8da0000000-7f8da0021000 rw-p 00000000 00:00 0
7f8da0021000-7f8da4000000 ---p 00000000 00:00 0
7f8da4000000-7f8da4021000 rw-p 00000000 00:00 0
7f8da4021000-7f8da8000000 ---p 00000000 00:00 0
7f8da8000000-7f8da8021000 rw-p 00000000 00:00 0
7f8da8021000-7f8dac000000 ---p 00000000 00:00 0
7f8dac000000-7f8dac021000 rw-p 00000000 00:00 0
7f8dac021000-7f8db0000000 ---p 00000000 00:00 0
7f8db0000000-7f8db0021000 rw-p 00000000 00:00 0
7f8db0021000-7f8db4000000 ---p 00000000 00:00 0
7f8db4000000-7f8db4021000 rw-p 00000000 00:00 0
7f8db4021000-7f8db8000000 ---p 00000000 00:00 0
7f8db8000000-7f8db8021000 rw-p 00000000 00:00 0
7f8db8021000-7f8dbc000000 ---p 00000000 00:00 0
7f8dbc000000-7f8dbc021000 rw-p 00000000 00:00 0
7f8dbc021000-7f8dc0000000 ---p 00000000 00:00 0
7f8dc0000000-7f8dc0001000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0001000-7f8dc0002000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0002000-7f8dc0003000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0003000-7f8dc0004000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0004000-7f8dc0005000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0005000-7f8dc0006000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0006000-7f8dc0007000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0007000-7f8dc0008000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0008000-7f8dc0009000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0009000-7f8dc000a000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000a000-7f8dc000b000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000b000-7f8dc000c000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000c000-7f8dc000d000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000d000-7f8dc000e000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000e000-7f8dc000f000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc000f000-7f8dc0010000 rw-s 00000000 00:05 14910 /dev/nvidia1
7f8dc0010000-7f8dd0000000 ---p 00000000 00:00 0
7f8dd01be000-7f8dd023e000 rw-p 00000000 00:00 0
7f8dd023e000-7f8dd023f000 ---p 00000000 00:00 0
7f8dd023f000-7f8dd0a40000 rw-p 00000000 00:00 0
7f8dd0a40000-7f8dd0a41000 ---p 00000000 00:00 0
7f8dd0a41000-7f8dd1242000 rw-p 00000000 00:00 0
7f8dd1242000-7f8dd1243000 ---p 00000000 00:00 0
7f8dd1243000-7f8dd1a44000 rw-p 00000000 00:00 0
7f8dd1a44000-7f8dd1a45000 ---p 00000000 00:00 0
7f8dd1a45000-7f8dd2246000 rw-p 00000000 00:00 0
7f8dd2246000-7f8dd2247000 ---p 00000000 00:00 0
7f8dd2247000-7f8dd2a48000 rw-p 00000000 00:00 0
7f8dd2a48000-7f8dd2a49000 ---p 00000000 00:00 0
7f8dd2a49000-7f8dd324a000 rw-p 00000000 00:00 0 Aborted
Can not find the file val.xml
Thank you for sharing the codes!
I tried to run your code but meet an error:
FileNotFoundError: [Errno 2] No such file or directory: '/home/dddzz/worksapce/Datasets/WIDERFace/WIDER_val/Annotations/val.xml'
How can I get the file, val.xml ?
How to convert outputs of TinaFace model into bounding boxes?
Hi,
Thank you for your great work!
I am reading your TinaFace paper and see that the outputs of TinaFace are in shape W x H x 4A. So I was wondering how do you convert those outputs into bounding boxes?
Question about ann_file from ${VEDADET_DIR}/configs/trainval/tinaface/tinaface.py for training or validation on WIDER FACE
Hi! First of all, thank you for your great work on single stage object detection!
I'm currently trying to reproduce detection results of TinaFace on WIDER FACE val written in the paper.
However, I have no idea about what file path I must write in ann_file from ${VEDADET_DIR}/configs/trainval/tinaface/tinaface.py for WIDER FACE training or validation.
At fisrt, I suspected it should be wider_face_train_bbx_gt.txt or wider_face_val_bbx_gt.txt from wider_face_split.zip.
However, it seems fileio.list_from_file from ${VEDADET_DIR}/vedadet/datasets/widerface.py doesn't return image ids appropriately.
According to the implementation of fileio.list_from_file, the appropriate file for ann_file seems to be a file containing only the image file name, such as wider_face_test_filelist.txt in from wider_face_split.zip.
Is it correct? Or am I missing something?
About img_norm_cfg in tinaface.py
Thanks for this great work. Tinaface use resnet50 as backbone and download pretrained model from pytorch official website. The official pytorch resnet50 use norm std as [58.395, 57.12, 57.375], whereas the std of img_norm_cfg in tinaface.py is [1, 1, 1]. Is there something I understand wrong?
[Possible Bug Fix]Making Config Class OS Agnostic
Hi, First of all thanks for creating this wonderful project.
I plan to use some parts of your project for my work. While studying the code in your project I realized that your Config class makes use of tempfile and shutil simultaneously, which causes a problem in windows software.
The problem arises when you create the tempfile using NamedTemporaryFile and then use shutils.copyfile. Once the temporary file is created it is opened automatically, then when you use shutils.copyfile, it tries to open the file again and windows doesn't allow it. So an easy workaround would be to close automatic deletion of the file and close the file before copying stuff into it. Later you can reopen the file and finally close and manually delete it.
So on high level:
temp_file = NamedTemporaryFile(delete=False)
temp_file.close()
shutil.copyfile(src_file, temp_file)
temp_file = open(temp_file_path)
# Code Goes Here
temp_file.close()
os.unlinkI will mention the complete modified _file2dict method here for reference:
def _file2dict(filename):
filename = osp.abspath(osp.expanduser(filename))
check_file_exist(filename)
if filename.endswith('.py'):
with tempfile.TemporaryDirectory() as temp_config_dir:
temp_config_file = tempfile.NamedTemporaryFile(
dir=temp_config_dir, suffix='.py', delete=False)
temp_config_file_name = temp_config_file.name
temp_config_name = osp.basename(temp_config_file_name)
temp_config_file.close()
shutil.copyfile(filename,
osp.join(temp_config_dir, temp_config_name))
temp_config_file = open(temp_config_file_name, 'a')
temp_module_name = osp.splitext(temp_config_name)[0]
sys.path.insert(0, temp_config_dir)
Config._validate_py_syntax(filename)
mod = import_module(temp_module_name)
sys.path.pop(0)
cfg_dict = {
name: value
for name, value in mod.__dict__.items()
if not name.startswith('__')
}
# delete imported module
del sys.modules[temp_module_name]
# close temp file
temp_config_file.close()
os.unlink(temp_config_file_name)
elif filename.endswith(('.yml', '.yaml', '.json')):
from .. import fileio
cfg_dict = fileio.load(filename)
else:
raise IOError('Only py/yml/yaml/json type are supported now!')
cfg_text = filename + '\n'
with open(filename, 'r') as f:
cfg_text += f.read()
if BASE_KEY in cfg_dict:
cfg_dir = osp.dirname(filename)
base_filename = cfg_dict.pop(BASE_KEY)
base_filename = base_filename if isinstance(
base_filename, list) else [base_filename]
cfg_dict_list = list()
cfg_text_list = list()
for f in base_filename:
_cfg_dict, _cfg_text = Config._file2dict(osp.join(cfg_dir, f))
cfg_dict_list.append(_cfg_dict)
cfg_text_list.append(_cfg_text)
base_cfg_dict = dict()
for c in cfg_dict_list:
if len(base_cfg_dict.keys() & c.keys()) > 0:
raise KeyError('Duplicate key is not allowed among bases')
base_cfg_dict.update(c)
base_cfg_dict = Config._merge_a_into_b(cfg_dict, base_cfg_dict)
cfg_dict = base_cfg_dict
# merge cfg_text
cfg_text_list.append(cfg_text)
cfg_text = '\n'.join(cfg_text_list)
return cfg_dict, cfg_textP.S - I apologize for not creating a proper pull request, my schedule is a bit tight these days.
Unable to reproduce results on widerface using tinaface
I am trying to reproduce the widerface results furnished here: https://github.com/Media-Smart/vedadet/tree/main/configs/trainval/tinaface.
I prepared the data as suggested in the Data Preparation section. I also did the filtering step using python configs/trainval/tinaface/filter_widerface_val.py. With the pretrained model of R50-FPN-BN, I ran the evaluation script configs/trainval/tinaface/test_widerface.py. Here are my results:
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 3226/3226, 0.5 task/s, elapsed: 5890s, ETA: 0s
+-------+-------+----------+--------+-------+
| class | gts | dets | recall | ap |
+-------+-------+----------+--------+-------+
| face | 31957 | 65363592 | 0.995 | 0.916 |
+-------+-------+----------+--------+-------+
| mAP | | | | 0.916 |
+-------+-------+----------+--------+-------+
From my results above, the mAP matches with your published results. But,
- The number of detections I get is
dets=65363592. Why is this difference indetsnot affecting the mAP? - Why do I get more detections in spite of the filtering step?
- I do not see the AP for easy, medium and hard subsets. How do I get these results?
- This evaluation has taken approximately 98 mins to complete on 3226 widerface validation images on GeForce GTX1080. Is there a way I can improve the speed?
Training tinaface on mmdetection
I'm trying to train a compatible model to tinaface on mmdetection repo.
The only difference is that I don't use the IOU-aware head, but normal RetinaHead.
On the first batches, I can see that on mmdetection the bbox loss is twice higher than vedadet. Maybe you can explain that?
Do you use different weights initialization than mmdetection?
I was really surprised by that because I see your code is based on mmdetection (it actually a fork, although you didn't use github fork)
Do you know how can TinaFace be run without GPU (and CUDA)?
I am getting OSError: CUDA is required to compile vedadet after running pip install -v -e . is understandable given your requirements, but I wonder if you know any easy way how the repo could be run even on laptop that has only CPU?
train error
(veda) root@linkdata-X299-WU8:/media/linkdata/zs/vedadet# bash tools/dist_trainval.sh configs/trainval/retinanet/retinanet.py 0
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
loading annotations into memory...
Done (t=0.01s)
creating index...
index created!
2020-12-02 11:57:16,139 - vedadet - INFO - Loading weights from /media/linkdata/zs/vedadet/premodel/resnet50-19c8e357.pth
2020-12-02 11:57:16,316 - vedadet - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: backbone.fc.weight, backbone.fc.bias
missing keys in source state_dict: neck.lateral_convs.0.conv.weight, neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.weight, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.weight, neck.lateral_convs.2.conv.bias, neck.fpn_convs.0.conv.weight, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.weight, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.weight, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.weight, neck.fpn_convs.3.conv.bias, neck.fpn_convs.4.conv.weight, neck.fpn_convs.4.conv.bias, bbox_head.cls_convs.0.conv.weight, bbox_head.cls_convs.0.conv.bias, bbox_head.cls_convs.1.conv.weight, bbox_head.cls_convs.1.conv.bias, bbox_head.cls_convs.2.conv.weight, bbox_head.cls_convs.2.conv.bias, bbox_head.cls_convs.3.conv.weight, bbox_head.cls_convs.3.conv.bias, bbox_head.reg_convs.0.conv.weight, bbox_head.reg_convs.0.conv.bias, bbox_head.reg_convs.1.conv.weight, bbox_head.reg_convs.1.conv.bias, bbox_head.reg_convs.2.conv.weight, bbox_head.reg_convs.2.conv.bias, bbox_head.reg_convs.3.conv.weight, bbox_head.reg_convs.3.conv.bias, bbox_head.retina_cls.weight, bbox_head.retina_cls.bias, bbox_head.retina_reg.weight, bbox_head.retina_reg.bias
2020-12-02 11:57:16,473 - vedadet - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: backbone.fc.weight, backbone.fc.bias
missing keys in source state_dict: neck.lateral_convs.0.conv.weight, neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.weight, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.weight, neck.lateral_convs.2.conv.bias, neck.fpn_convs.0.conv.weight, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.weight, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.weight, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.weight, neck.fpn_convs.3.conv.bias, neck.fpn_convs.4.conv.weight, neck.fpn_convs.4.conv.bias, bbox_head.cls_convs.0.conv.weight, bbox_head.cls_convs.0.conv.bias, bbox_head.cls_convs.1.conv.weight, bbox_head.cls_convs.1.conv.bias, bbox_head.cls_convs.2.conv.weight, bbox_head.cls_convs.2.conv.bias, bbox_head.cls_convs.3.conv.weight, bbox_head.cls_convs.3.conv.bias, bbox_head.reg_convs.0.conv.weight, bbox_head.reg_convs.0.conv.bias, bbox_head.reg_convs.1.conv.weight, bbox_head.reg_convs.1.conv.bias, bbox_head.reg_convs.2.conv.weight, bbox_head.reg_convs.2.conv.bias, bbox_head.reg_convs.3.conv.weight, bbox_head.reg_convs.3.conv.bias, bbox_head.retina_cls.weight, bbox_head.retina_cls.bias, bbox_head.retina_reg.weight, bbox_head.retina_reg.bias
training pause at waiting for data when trianing dataset increase to one hundred thousand images?
2020-12-16 20:11:46,235 - vedadet - INFO - Epoch [1][1400/4732] lr: 0.00375, loss_cls: 0.2021, loss_bbox: 0.5325, loss_iou: 0.5654, loss: 1.2999
2020-12-16 20:12:33,962 - vedadet - INFO - Epoch [1][1500/4732] lr: 0.00375, loss_cls: 0.2406, loss_bbox: 0.6577, loss_iou: 0.6214, loss: 1.5197
File "tools/trainval.py", line 65, in
main()
File "tools/trainval.py", line 61, in main
trainval(cfg, distributed, logger)
File "/mnt/data2/code/vedadet2/vedadet/assembler/trainval.py", line 78, in trainval
looper.start(cfg.max_epochs)
File "/mnt/data2/code/vedadet2/vedacore/loopers/epoch_based_looper.py", line 29, in start
self.epoch_loop(mode)
File "/mnt/data2/code/vedadet2/vedacore/loopers/epoch_based_looper.py", line 15, in epoch_loop
for idx, data in enumerate(dataloader):
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in next
data = self._next_data()
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 974, in _next_data
idx, data = self._get_data()
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 941, in _get_data
success, data = self._try_get_data()
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 779, in _try_get_data
data = self._data_queue.get(timeout=timeout)
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/multiprocessing/queues.py", line 104, in get
if not self._poll(timeout):
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/multiprocessing/connection.py", line 257, in poll
return self._poll(timeout)
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/multiprocessing/connection.py", line 414, in _poll
r = wait([self], timeout)
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/multiprocessing/connection.py", line 921, in wait
ready = selector.select(timeout)
File "/home/environment/anaconda2/envs/vedadet2/lib/python3.7/selectors.py", line 415, in select
fd_event_list = self._selector.poll(timeout)
ImportError: cannot import name 'deform_conv_ext'
Reproduce TinaFace fellow https://github.com/Media-Smart/vedadet/tree/main/configs/trainval/tinaface/README.md
Evaluation(b): python configs/trainval/tinaface/test_widerface.py configs/trainval/tinaface/tinaface.py weight_path
Error message was as fellow. Anyone have the same problem ??? Thank you for answering~~~
Traceback (most recent call last):
File "test_widerface.py", line 9, in
from vedadet.datasets import build_dataloader, build_dataset
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/init.py", line 1, in
from . import assembler, bridge, criteria, datasets, engines, misc, models, ops
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/assembler/init.py", line 1, in
from .trainval import trainval
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/assembler/trainval.py", line 6, in
from vedadet.datasets import build_dataloader, build_dataset
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/datasets/init.py", line 2, in
from .coco import CocoDataset
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/datasets/coco.py", line 14, in
from .custom import CustomDataset
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/datasets/custom.py", line 9, in
from .pipelines import Compose
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/datasets/pipelines/init.py", line 8, in
from .transforms import (Albu, Expand, MinIoURandomCrop, Normalize, Pad,
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/datasets/pipelines/transforms.py", line 9, in
from vedadet.misc.bbox import bbox_overlaps
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/init.py", line 1, in
from .assigners import MaxIoUAssigner
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/assigners/init.py", line 1, in
from .approx_max_iou_assigner import ApproxMaxIoUAssigner
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/assigners/approx_max_iou_assigner.py", line 6, in
from ..iou_calculators import build_iou_calculator
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/iou_calculators/init.py", line 2, in
from .iou2d_calculator import BboxOverlaps2D
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/iou_calculators/iou2d_calculator.py", line 4, in
from ..bbox import bbox_overlaps
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/misc/bbox/bbox.py", line 6, in
from vedadet.ops import batched_nms
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/ops/init.py", line 1, in
from .dcn import (DeformConv, DeformConvPack, DeformRoIPooling,
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/ops/dcn/init.py", line 1, in
from .deform_conv import (DeformConv, DeformConvPack, ModulatedDeformConv,
File "/dfsdata2/jiangjl5_data/vedadet/vedadet/ops/dcn/deform_conv.py", line 11, in
from . import deform_conv_ext
ImportError: cannot import name 'deform_conv_ext'
building nms ops fails during installation
The command pip install -v -e. --log piplog.txt, the installation fails while trying to build the nms related parts.
2021-05-31T08:51:28,118 Using pip 21.1.1 from /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip (python 3.8)
2021-05-31T08:51:28,124 Non-user install because site-packages writeable
2021-05-31T08:51:28,368 Created temporary directory: /tmp/pip-ephem-wheel-cache-f0e1dx_v
2021-05-31T08:51:28,368 Created temporary directory: /tmp/pip-req-tracker-h4kqazup
2021-05-31T08:51:28,369 Initialized build tracking at /tmp/pip-req-tracker-h4kqazup
2021-05-31T08:51:28,369 Created build tracker: /tmp/pip-req-tracker-h4kqazup
2021-05-31T08:51:28,369 Entered build tracker: /tmp/pip-req-tracker-h4kqazup
2021-05-31T08:51:28,369 Created temporary directory: /tmp/pip-install-u38ho2hv
2021-05-31T08:51:28,399 Obtaining file:///home_nfs/manuel/gal/vedadet
2021-05-31T08:51:28,400 Added file:///home_nfs/manuel/gal/vedadet to build tracker '/tmp/pip-req-tracker-h4kqazup'
2021-05-31T08:51:28,400 Running setup.py (path:/home_nfs/manuel/gal/vedadet/setup.py) egg_info for package from file:///home_nfs/manuel/gal/vedadet
2021-05-31T08:51:28,400 Created temporary directory: /tmp/pip-pip-egg-info-y9fhdtti
2021-05-31T08:51:28,400 Running command python setup.py egg_info
2021-05-31T08:51:30,710 running egg_info
2021-05-31T08:51:30,711 creating /tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info
2021-05-31T08:51:30,711 writing /tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/PKG-INFO
2021-05-31T08:51:30,712 writing dependency_links to /tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/dependency_links.txt
2021-05-31T08:51:30,712 writing requirements to /tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/requires.txt
2021-05-31T08:51:30,712 writing top-level names to /tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/top_level.txt
2021-05-31T08:51:30,712 writing manifest file '/tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/SOURCES.txt'
2021-05-31T08:51:30,871 reading manifest file '/tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/SOURCES.txt'
2021-05-31T08:51:30,874 writing manifest file '/tmp/pip-pip-egg-info-y9fhdtti/vedadet.egg-info/SOURCES.txt'
2021-05-31T08:51:31,088 Source in /home_nfs/manuel/gal/vedadet has version 0.1.0, which satisfies requirement vedadet==0.1.0 from file:///home_nfs/manuel/gal/vedadet
2021-05-31T08:51:31,088 Removed vedadet==0.1.0 from file:///home_nfs/manuel/gal/vedadet from build tracker '/tmp/pip-req-tracker-h4kqazup'
2021-05-31T08:51:31,131 Requirement already satisfied: addict in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (2.4.0)
2021-05-31T08:51:31,132 Requirement already satisfied: terminaltables in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (3.1.0)
2021-05-31T08:51:31,133 Requirement already satisfied: opencv-python in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (4.5.2.52)
2021-05-31T08:51:31,134 Requirement already satisfied: torchvision>=0.7.0 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (0.9.1)
2021-05-31T08:51:31,134 Requirement already satisfied: pyyaml in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (5.4.1)
2021-05-31T08:51:31,135 Requirement already satisfied: yapf in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (0.31.0)
2021-05-31T08:51:31,136 Requirement already satisfied: imagecorruptions in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (1.1.2)
2021-05-31T08:51:31,137 Requirement already satisfied: mmpycocotools in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from vedadet==0.1.0) (12.0.3)
2021-05-31T08:51:31,142 Requirement already satisfied: numpy in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from torchvision>=0.7.0->vedadet==0.1.0) (1.20.3)
2021-05-31T08:51:31,143 Requirement already satisfied: pillow>=4.1.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from torchvision>=0.7.0->vedadet==0.1.0) (8.2.0)
2021-05-31T08:51:31,144 Requirement already satisfied: torch==1.8.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from torchvision>=0.7.0->vedadet==0.1.0) (1.8.1)
2021-05-31T08:51:31,148 Requirement already satisfied: typing-extensions in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from torch==1.8.1->torchvision>=0.7.0->vedadet==0.1.0) (3.10.0.0)
2021-05-31T08:51:31,158 Requirement already satisfied: scipy>=1.2.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from imagecorruptions->vedadet==0.1.0) (1.6.3)
2021-05-31T08:51:31,160 Requirement already satisfied: scikit-image>=0.15 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from imagecorruptions->vedadet==0.1.0) (0.18.1)
2021-05-31T08:51:31,217 Requirement already satisfied: PyWavelets>=1.1.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (1.1.1)
2021-05-31T08:51:31,219 Requirement already satisfied: networkx>=2.0 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (2.5.1)
2021-05-31T08:51:31,220 Requirement already satisfied: matplotlib!=3.0.0,>=2.0.0 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (3.4.2)
2021-05-31T08:51:31,221 Requirement already satisfied: imageio>=2.3.0 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (2.9.0)
2021-05-31T08:51:31,222 Requirement already satisfied: tifffile>=2019.7.26 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (2021.4.8)
2021-05-31T08:51:31,240 Requirement already satisfied: cycler>=0.10 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (0.10.0)
2021-05-31T08:51:31,241 Requirement already satisfied: kiwisolver>=1.0.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (1.3.1)
2021-05-31T08:51:31,242 Requirement already satisfied: pyparsing>=2.2.1 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (2.4.7)
2021-05-31T08:51:31,243 Requirement already satisfied: python-dateutil>=2.7 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (2.8.1)
2021-05-31T08:51:31,247 Requirement already satisfied: six in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from cycler>=0.10->matplotlib!=3.0.0,>=2.0.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (1.16.0)
2021-05-31T08:51:31,268 Requirement already satisfied: decorator<5,>=4.3 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from networkx>=2.0->scikit-image>=0.15->imagecorruptions->vedadet==0.1.0) (4.4.2)
2021-05-31T08:51:31,298 Requirement already satisfied: cython>=0.27.3 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from mmpycocotools->vedadet==0.1.0) (0.29.23)
2021-05-31T08:51:31,299 Requirement already satisfied: setuptools>=18.0 in /home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages (from mmpycocotools->vedadet==0.1.0) (52.0.0.post20210125)
2021-05-31T08:51:31,342 Created temporary directory: /tmp/pip-unpack-rprzhfke
2021-05-31T08:51:31,347 Installing collected packages: vedadet
2021-05-31T08:51:31,350 Running setup.py develop for vedadet
2021-05-31T08:51:31,350 Running command /home_nfs/manuel/miniconda/envs/vedadet/bin/python -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"'; __file__='"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' develop --no-deps
2021-05-31T08:51:33,533 running develop
2021-05-31T08:51:33,673 running egg_info
2021-05-31T08:51:33,674 writing vedadet.egg-info/PKG-INFO
2021-05-31T08:51:33,735 writing dependency_links to vedadet.egg-info/dependency_links.txt
2021-05-31T08:51:33,742 writing requirements to vedadet.egg-info/requires.txt
2021-05-31T08:51:33,746 writing top-level names to vedadet.egg-info/top_level.txt
2021-05-31T08:51:33,887 reading manifest file 'vedadet.egg-info/SOURCES.txt'
2021-05-31T08:51:33,894 writing manifest file 'vedadet.egg-info/SOURCES.txt'
2021-05-31T08:51:33,899 running build_ext
2021-05-31T08:51:33,919 building 'vedadet.ops.nms.nms_ext' extension
2021-05-31T08:51:34,049 Emitting ninja build file /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/build.ninja...
2021-05-31T08:51:34,050 Compiling objects...
2021-05-31T08:51:34,050 Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
2021-05-31T08:51:34,311 [1/1] /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/vedadet/ops/nms/src/cuda/nms_kernel.o.d -DWITH_CUDA -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/TH -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home_nfs/manuel/miniconda/envs/vedadet/include/python3.8 -c -c /home_nfs/manuel/gal/vedadet/vedadet/ops/nms/src/cuda/nms_kernel.cu -o /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/vedadet/ops/nms/src/cuda/nms_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=nms_ext -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=compute_61 -gencode=arch=compute_61,code=sm_61 -std=c++14
2021-05-31T08:51:34,311 FAILED: /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/vedadet/ops/nms/src/cuda/nms_kernel.o
2021-05-31T08:51:34,311 /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/vedadet/ops/nms/src/cuda/nms_kernel.o.d -DWITH_CUDA -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/TH -I/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home_nfs/manuel/miniconda/envs/vedadet/include/python3.8 -c -c /home_nfs/manuel/gal/vedadet/vedadet/ops/nms/src/cuda/nms_kernel.cu -o /home_nfs/manuel/gal/vedadet/build/temp.linux-x86_64-3.8/vedadet/ops/nms/src/cuda/nms_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=nms_ext -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=compute_61 -gencode=arch=compute_61,code=sm_61 -std=c++14
2021-05-31T08:51:34,312 nvcc fatal : Unknown option '-generate-dependencies-with-compile'
2021-05-31T08:51:34,312 ninja: build stopped: subcommand failed.
2021-05-31T08:51:34,339 Traceback (most recent call last):
2021-05-31T08:51:34,339 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1667, in _run_ninja_build
2021-05-31T08:51:34,340 subprocess.run(
2021-05-31T08:51:34,340 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/subprocess.py", line 512, in run
2021-05-31T08:51:34,340 raise CalledProcessError(retcode, process.args,
2021-05-31T08:51:34,341 subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
2021-05-31T08:51:34,341 The above exception was the direct cause of the following exception:
2021-05-31T08:51:34,342 Traceback (most recent call last):
2021-05-31T08:51:34,342 File "<string>", line 1, in <module>
2021-05-31T08:51:34,342 File "/home_nfs/manuel/gal/vedadet/setup.py", line 119, in <module>
2021-05-31T08:51:34,342 setup(
2021-05-31T08:51:34,343 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/setuptools/__init__.py", line 153, in setup
2021-05-31T08:51:34,343 return distutils.core.setup(**attrs)
2021-05-31T08:51:34,343 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/core.py", line 148, in setup
2021-05-31T08:51:34,343 dist.run_commands()
2021-05-31T08:51:34,344 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/dist.py", line 966, in run_commands
2021-05-31T08:51:34,344 self.run_command(cmd)
2021-05-31T08:51:34,344 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/dist.py", line 985, in run_command
2021-05-31T08:51:34,344 cmd_obj.run()
2021-05-31T08:51:34,344 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/setuptools/command/develop.py", line 34, in run
2021-05-31T08:51:34,345 self.install_for_development()
2021-05-31T08:51:34,345 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/setuptools/command/develop.py", line 136, in install_for_development
2021-05-31T08:51:34,345 self.run_command('build_ext')
2021-05-31T08:51:34,345 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/cmd.py", line 313, in run_command
2021-05-31T08:51:34,346 self.distribution.run_command(command)
2021-05-31T08:51:34,346 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/dist.py", line 985, in run_command
2021-05-31T08:51:34,346 cmd_obj.run()
2021-05-31T08:51:34,346 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 79, in run
2021-05-31T08:51:34,347 _build_ext.run(self)
2021-05-31T08:51:34,347 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
2021-05-31T08:51:34,347 _build_ext.build_ext.run(self)
2021-05-31T08:51:34,347 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/command/build_ext.py", line 340, in run
2021-05-31T08:51:34,347 self.build_extensions()
2021-05-31T08:51:34,347 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 708, in build_extensions
2021-05-31T08:51:34,348 build_ext.build_extensions(self)
2021-05-31T08:51:34,348 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
2021-05-31T08:51:34,348 _build_ext.build_ext.build_extensions(self)
2021-05-31T08:51:34,348 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/command/build_ext.py", line 449, in build_extensions
2021-05-31T08:51:34,348 self._build_extensions_serial()
2021-05-31T08:51:34,348 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/command/build_ext.py", line 474, in _build_extensions_serial
2021-05-31T08:51:34,348 self.build_extension(ext)
2021-05-31T08:51:34,349 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 196, in build_extension
2021-05-31T08:51:34,349 _build_ext.build_extension(self, ext)
2021-05-31T08:51:34,349 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/distutils/command/build_ext.py", line 528, in build_extension
2021-05-31T08:51:34,349 objects = self.compiler.compile(sources,
2021-05-31T08:51:34,349 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 529, in unix_wrap_ninja_compile
2021-05-31T08:51:34,349 _write_ninja_file_and_compile_objects(
2021-05-31T08:51:34,349 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1354, in _write_ninja_file_and_compile_objects
2021-05-31T08:51:34,349 _run_ninja_build(
2021-05-31T08:51:34,350 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1683, in _run_ninja_build
2021-05-31T08:51:34,350 raise RuntimeError(message) from e
2021-05-31T08:51:34,350 RuntimeError: Error compiling objects for extension
2021-05-31T08:51:34,545 ERROR: Command errored out with exit status 1: /home_nfs/manuel/miniconda/envs/vedadet/bin/python -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"'; __file__='"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.
2021-05-31T08:51:34,546 Exception information:
2021-05-31T08:51:34,546 Traceback (most recent call last):
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/cli/base_command.py", line 180, in _main
2021-05-31T08:51:34,546 status = self.run(options, args)
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/cli/req_command.py", line 204, in wrapper
2021-05-31T08:51:34,546 return func(self, options, args)
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/commands/install.py", line 393, in run
2021-05-31T08:51:34,546 installed = install_given_reqs(
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/req/__init__.py", line 77, in install_given_reqs
2021-05-31T08:51:34,546 requirement.install(
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/req/req_install.py", line 758, in install
2021-05-31T08:51:34,546 install_editable_legacy(
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/operations/install/editable_legacy.py", line 44, in install_editable
2021-05-31T08:51:34,546 call_subprocess(
2021-05-31T08:51:34,546 File "/home_nfs/manuel/miniconda/envs/vedadet/lib/python3.8/site-packages/pip/_internal/utils/subprocess.py", line 244, in call_subprocess
2021-05-31T08:51:34,546 raise InstallationSubprocessError(proc.returncode, command_desc)
2021-05-31T08:51:34,546 pip._internal.exceptions.InstallationSubprocessError: Command errored out with exit status 1: /home_nfs/manuel/miniconda/envs/vedadet/bin/python -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"'; __file__='"'"'/home_nfs/manuel/gal/vedadet/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' develop --no-deps Check the logs for full command output.
2021-05-31T08:51:34,565 Removed build tracker: '/tmp/pip-req-tracker-h4kqazup'
How do I resolve this? Are there some known workarounds to this issue? My cmake version is `3.13.2`. I am installing on an ubuntu18.04 machine.
Facing issue when running "pip install -v -e ." on windows machine
Facing issue when running "pip install -v -e ." on windows machine
config{
windows:10
cuda 10.2
python:3.8}
TinaFace weights
Could you please tell me where I can find the TinaFace model weights? thanks in advance
how to inference on webcam or video?
In infer.py you did it by data_pipeline. How to handle it when source is Webcam or Video frames?
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.