open-mmlab / mmaction Goto Github PK

Hopefully this is my last error in the installation part :/
So I am trying to do Install MMAction.
when i run ./compile.sh it gives me:
bash: ./compile.sh: Permission denied

so i did sudo bash compile.sh

but then I got

Building package resample2d
Traceback (most recent call last):
  File "setup.py", line 3, in <module>
    import torch
ImportError: No module named torch
Building package trajectory_conv...
Traceback (most recent call last):
  File "setup.py", line 3, in <module>
    import torch
ImportError: No module named torch
Building roi align op...
Traceback (most recent call last):
  File "setup.py", line 2, in <module>
    from torch.utils.cpp_extension import BuildExtension, CUDAExtension
ImportError: No module named torch.utils.cpp_extension
Building roi pool op...
Traceback (most recent call last):
  File "setup.py", line 2, in <module>
    from torch.utils.cpp_extension import BuildExtension, CUDAExtension
ImportError: No module named torch.utils.cpp_extension
Building nms op...
Traceback (most recent call last):
  File "setup.py", line 5, in <module>
    from Cython.Build import cythonize
ImportError: No module named Cython.Build
alireza@alireza:~/Desktop/mmaction$ 

I think the problem is that i have python 3.6 via using anaconda, but it cannot find that path.
because all the packages that it says i dont have i do have them.

alireza@alireza:~/Desktop/mmaction$ which python
/home/alireza/anaconda3/bin/python
alireza@alireza:~/Desktop/mmaction$ which cython
/home/alireza/anaconda3/bin/cython

can you please help me to make it to look at the right path. I think something is compile.sh should change but not sure what.

Thanks

How to generate TAG proposals?
In https://github.com/yjxiong/action-detection, by using python gen_bottom_up_proposals.py.

it seeems like denseflow needs to be compiled with OpenCV 2.4.13 and CUDA. However this version of OpenCV does not match with CUDA9.0+... And I can't compile OpenCV successfully. Is there any solution? This is a CentOS 7.6, cmake 3.15.0, gcc 6.5.0, Titan X.

Hi,

I follow steps from dense_flow install tutorial, first to install opencv-4.1.0, everything OK.

But when I use the command "make -j" to install dense flow, an error appears:

(base) root@79d763daaf2a:/yanghui_root/mmaction/third_party/dense_flow/build# make -j
[  7%] Building CXX object CMakeFiles/denseflow.dir/src/dense_flow.cpp.o
[ 14%] Building CXX object CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o
[ 21%] Building CXX object CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o
/yanghui_root/mmaction/third_party/dense_flow/src/dense_warp_flow_gpu.cpp:12:35: fatal error: opencv2/xfeatures2d.hpp: No such file or directory
compilation terminated.
CMakeFiles/denseflow.dir/build.make:134: recipe for target 'CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o' failed
make[2]: *** [CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
/yanghui_root/mmaction/third_party/dense_flow/src/dense_flow.cpp:6:31: fatal error: opencv2/optflow.hpp: No such file or directory
compilation terminated.
CMakeFiles/denseflow.dir/build.make:86: recipe for target 'CMakeFiles/denseflow.dir/src/dense_flow.cpp.o' failed
make[2]: *** [CMakeFiles/denseflow.dir/src/dense_flow.cpp.o] Error 1
/yanghui_root/mmaction/third_party/dense_flow/src/dense_flow_gpu.cpp:5:35: fatal error: opencv2/xfeatures2d.hpp: No such file or directory
compilation terminated.
CMakeFiles/denseflow.dir/build.make:110: recipe for target 'CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o' failed
make[2]: *** [CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o] Error 1
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/denseflow.dir/all' failed
make[1]: *** [CMakeFiles/denseflow.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2

What's the problem about this?
I use Ubuntu 16.04, cuda9.0, and opencv4.1.0 is installed OK.

First. thanks for your great work. I can run the TSN2D successfully. I want to run the TSN3D to compare to 2D. Can you supply the 3D model config. or it is same as the 2D config ? can you supply the paper about the difference between them. thanks advance.

Hi

Dear friend, I am training with i3d on my personal dataset with --validation flag.
If i want to performs evaluation every 2 or 3 epochs during the training, where can I change the defalut k?

Thanks

Hi, I used the https://github.com/open-mmlab/mmaction/blob/master/data_tools/kinetics400/download_videos.sh script to download Kinetics dataset. However, I encountered the following error:

line 19: [: too many arguments
line 27: [: too many arguments

Actually the videos are all downloaded ok. It is just the classes in the folder still have white spaces. It seems this line if [ $class != $newclass ] is not working correctly. I don't know if this is just me, or anyone also having this issue? Thank you.

I gent this error when i was trying to install opencv after I run this:
cmake -D CMAKE_BUILD_TYPE=RELEASE -D WITH_TBB=ON -D WITH_V4L=ON ..
not sure why...

error occurred at cmake step

-DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=resample2d_cuda -D_GLIBCXX_USE_CXX11_ABI=0
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from resample2d_cuda.cc:2:0:
/home/alex/anaconda3/envs/mmaction/lib/python3.5/site-packages/torch/include/torch/csrc/api/include/torch/torch.h:7:2: warning: #warning "Including torch/torch.h for C++ extensions is deprecated. Please include torch/extension.h" [-Wcpp]
#warning \

I have tried GCC 7.4, 5.5, 4.8. All of them does not work.
My environment
CUDA 10 (Although using nvcc -V it shows 9.1.85)
Pytorch 1.1 (Not from source, tried from source and still does not work)

my environment:ubuntu16.04,opencv3.4.0

the error log as blew:
/dense_flow/build$ cmake .. && make -j
-- Boost version: 1.65.1
-- Found the following Boost libraries:
-- python
-- Configuring done
-- Generating done
-- Build files have been written to: /home/yyk/ACTION/mmaction/third_party/dense_flow/build
Scanning dependencies of target denseflow
[ 7%] Building CXX object CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o
[ 14%] Building CXX object CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o
/home/yyk/ACTION/mmaction/third_party/dense_flow/src/dense_warp_flow_gpu.cpp:12:10: fatal error: opencv2/xfeatures2d.hpp: No such file or directory
#include "opencv2/xfeatures2d.hpp"
^~~~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
/home/yyk/ACTION/mmaction/third_party/dense_flow/src/dense_flow_gpu.cpp:5:10: fatal error: opencv2/xfeatures2d.hpp: No such file or directory
#include "opencv2/xfeatures2d.hpp"
^~~~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
CMakeFiles/denseflow.dir/build.make:134: recipe for target 'CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o' failed
make[2]: *** [CMakeFiles/denseflow.dir/src/dense_warp_flow_gpu.cpp.o] Error 1
make[2]: *** Waiting for unfinished jobs....
CMakeFiles/denseflow.dir/build.make:110: recipe for target 'CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o' failed
make[2]: *** [CMakeFiles/denseflow.dir/src/dense_flow_gpu.cpp.o] Error 1
CMakeFiles/Makefile2:215: recipe for target 'CMakeFiles/denseflow.dir/all' failed
make[1]: *** [CMakeFiles/denseflow.dir/all] Error 2

thanks in advance!

when i use i3d_kinetics_3d_rgb_r50_c3d_inflate3x1x1_seg1_f32s2_b8_g8_imagenet this config to reproduce the kinetics result, this comes to an error :

/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [5,0,0] Assertion `t >= 0 && t < n_classes` failed.
/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [3,0,0] Assertion `t >= 0 && t < n_classes` failed.
Traceback (most recent call last):
  File "./tools/train_recognizer.py", line 90, in <module>
    main()
  File "./tools/train_recognizer.py", line 86, in main
    logger=logger)
  File "/home/wangtao1/mmaction/mmaction/apis/train.py", line 57, in train_network
    _dist_train(model, dataset, cfg, validate=validate)
  File "/home/wangtao1/mmaction/mmaction/apis/train.py", line 102, in _dist_train
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/usr/local/lib/python3.6/site-packages/mmcv/runner/runner.py", line 356, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/usr/local/lib/python3.6/site-packages/mmcv/runner/runner.py", line 262, in train
    self.model, data_batch, train_mode=True, **kwargs)
  File "/home/wangtao1/mmaction/mmaction/apis/train.py", line 37, in batch_processor
    loss, log_vars = parse_losses(losses)
  File "/home/wangtao1/mmaction/mmaction/apis/train.py", line 30, in parse_losses
    log_vars[name] = log_vars[name].item()
RuntimeError: CUDA error: device-side assert triggered
terminate called after throwing an instance of 'c10::Error'
  what():  CUDA error: device-side assert triggered (insert_events at /pytorch/aten/src/THC/THCCachingAllocator.cpp:470)
frame #0: std::function<std::string ()>::operator()() const + 0x11 (0x7f719f2e6021 in /usr/local/lib64/python3.6/site-packages/torch/lib/libc10.so)
frame #1: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x2a (0x7f719f2e58ea in /usr/local/lib64/python3.6/site-packages/torch/lib/libc10.so)
frame #2: <unknown function> + 0x13f6002 (0x7f70fffed002 in /usr/local/lib64/python3.6/site-packages/torch/lib/libcaffe2_gpu.so)
frame #3: at::TensorImpl::release_resources() + 0x50 (0x7f70f5433440 in /usr/local/lib64/python3.6/site-packages/torch/lib/libcaffe2.so)
frame #4: <unknown function> + 0x2af03b (0x7f7197d5003b in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #5: <unknown function> + 0x3174e3 (0x7f7197db84e3 in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #6: torch::autograd::deleteFunction(torch::autograd::Function*) + 0x198 (0x7f7197d52878 in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #7: std::_Sp_counted_base<(__gnu_cxx::_Lock_policy)2>::_M_release() + 0x45 (0x7f719f6050f5 in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #8: torch::autograd::Variable::Impl::release_resources() + 0x4a (0x7f7197fc2d5a in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch.so.1)
frame #9: <unknown function> + 0x124cfb (0x7f719f61bcfb in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #10: <unknown function> + 0x3204af (0x7f719f8174af in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #11: <unknown function> + 0x3204f1 (0x7f719f8174f1 in /usr/local/lib64/python3.6/site-packages/torch/lib/libtorch_python.so)
<omitting python frames>
frame #28: main + 0x119 (0x400a99 in /usr/bin/python3)
frame #29: __libc_start_main + 0xf5 (0x7f71aeb9a3d5 in /lib64/libc.so.6)
frame #30: /usr/bin/python3() [0x400c20]

anynone knows what is wrong?

im stuck in the **
Build OpenCV 4.1.0 from scratch (due to some custom settings)
**
I am trying to build the opencv but this happens over and over

/home/alireza/Desktop/mmaction/third_party/opencv_contrib-4.1.0/modules/xfeatures2d/src/boostdesc.cpp:653:37: fatal error: boostdesc_bgm.i: No such file or directory
compilation terminated.
modules/xfeatures2d/CMakeFiles/opencv_xfeatures2d.dir/build.make:425: recipe for target 'modules/xfeatures2d/CMakeFiles/opencv_xfeatures2d.dir/src/boostdesc.cpp.o' failed
make[2]: *** [modules/xfeatures2d/CMakeFiles/opencv_xfeatures2d.dir/src/boostdesc.cpp.o] Error 1
CMakeFiles/Makefile2:14075: recipe for target 'modules/xfeatures2d/CMakeFiles/opencv_xfeatures2d.dir/all' failed
make[1]: *** [modules/xfeatures2d/CMakeFiles/opencv_xfeatures2d.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....

I followed the installation guide in INSTALL.md but when I try to run compile.sh it fails with a series of compile time errors. Some of the first errors say like this:

/usr/local/cuda/bin/nvcc -I/home/janos/anaconda3/envs/mmaction/lib/python3.7/site-packages/torch/include -I/home/janos/anaconda3/envs/mmaction/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/janos/anaconda3/envs/mmaction/lib/python3.7/site-packages/torch/include/TH -I/home/janos/anaconda3/envs/mmaction/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/janos/anaconda3/envs/mmaction/include/python3.7m -c resample2d_kernel.cu -o build/temp.linux-x86_64-3.7/resample2d_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --compiler-options '-fPIC' -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_70,code=compute_70 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=resample2d_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
/usr/include/c++/6/tuple: In instantiation of ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’:
/usr/include/c++/6/tuple:626:248:   required by substitution of ‘template<class ... _UElements, typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> > constexpr std::tuple< <template-parameter-1-1> >::tuple(_UElements&& ...) [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; typename std::enable_if<(((std::_TC<(sizeof... (_UElements) == 1), at::Tensor, at::Tensor, at::Tensor>::_NotSameTuple<_UElements ...>() && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_MoveConstructibleTuple<_UElements ...>()) && std::_TC<(1ul == sizeof... (_UElements)), at::Tensor, at::Tensor, at::Tensor>::_ImplicitlyMoveConvertibleTuple<_UElements ...>()) && (3ul >= 1)), bool>::type <anonymous> = <missing>]’
/home/janos/anaconda3/envs/mmaction/lib/python3.7/site-packages/torch/include/ATen/core/TensorMethods.h:1181:57:   required from here
/usr/include/c++/6/tuple:483:67: error: mismatched argument pack lengths while expanding ‘std::is_constructible<_Elements, _UElements&&>’
       return __and_<is_constructible<_Elements, _UElements&&>...>::value;
                                                                   ^~~~~
/usr/include/c++/6/tuple:484:1: error: body of constexpr function ‘static constexpr bool std::_TC<<anonymous>, _Elements>::_MoveConstructibleTuple() [with _UElements = {std::tuple<at::Tensor, at::Tensor, at::Tensor>}; bool <anonymous> = true; _Elements = {at::Tensor, at::Tensor, at::Tensor}]’ not a return-statement
     }
 ^

I use ubuntu 18.10 and CUDA 9.0 and anaconda.

Failed to import ActivityNet evaluation toolbox. Did you clone with"--recursive"?
Failed to import ActivityNet evaluation toolbox. Did you clone with"--recursive"?
Traceback (most recent call last):
File "tools/test_recognizer.py", line 10, in
from mmaction.models import build_recognizer, recognizers
File "/home/yyf/.local/lib/python3.6/site-packages/mmaction-0.1rc0+f83b052-py3.6.egg/mmaction/models/init.py", line 1, in
from .tenons.backbones import *
ModuleNotFoundError: No module named 'mmaction.models.tenons'

who can help me solve this problem？tkx

when I run the command './tools/dist_train_detector.sh configs/ava/ava_fast_rcnn_nl_r50_c4_1x_kinetics_pretrain_crop.py 4' for the spatial-temporal action detection model, an error appears:

Traceback (most recent call last):
  File "./tools/train_detector.py", line 90, in <module>
    main()
  File "./tools/train_detector.py", line 86, in main
    logger=logger)
  File "/yanghui_root/mmaction/mmaction/apis/train.py", line 57, in train_network
    _dist_train(model, dataset, cfg, validate=validate)
  File "/yanghui_root/mmaction/mmaction/apis/train.py", line 102, in _dist_train
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/root/anaconda3/lib/python3.7/site-packages/mmcv-0.2.8-py3.7.egg/mmcv/runner/runner.py", line 356, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/root/anaconda3/lib/python3.7/site-packages/mmcv-0.2.8-py3.7.egg/mmcv/runner/runner.py", line 258, in train
    for i, data_batch in enumerate(data_loader):
  File "/root/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 583, in __next__
    return self._process_next_batch(batch)
  File "/root/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 609, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
  File "/root/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 108, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/root/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 108, in <listcomp>
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/yanghui_root/mmaction/mmaction/datasets/ava_dataset.py", line 348, in __getitem__
    data = self.prepare_train_imgs(idx)
  File "/yanghui_root/mmaction/mmaction/datasets/ava_dataset.py", line 434, in prepare_train_imgs
    img_group_0=DC(to_tensor(img_group), stack=True, pad_dims=2),
TypeError: __init__() got an unexpected keyword argument 'pad_dims'

My mmcv version is mmcv-0.2.8.

Hi there, thank you for the wonderful codebase. I followed the Getting Started page to train a 2D TSN experiment on RGB images of UCF101 dataset.

./tools/dist_train_recognizer.sh configs/ucf101/tsn_rgb_bninception.py 8 --validate

I think I followed all the steps in the readme, but the best accuracy I can get is 84.31 (which is about 2% away from the number you reported, 86.41).

I also downloaded the reference model tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth and test it, the accuracy is indeed 86.41. This means your pre-trained model is good, and my data should be good too. Then the problem may lie in the training side, maybe I miss some important details.

Could you help me to reproduce the result? Let me know if you need more information. Thank you very much.

@zhaoyue-zephyrus I use test_detector.py to test thumos14, but get KeyError: 'SSN2D is not in the detector registry'.
I only use 20 videos of test(1574), modify the thumos14_tag_test_normalized_proposal_list.txt

How can I solve this problem?

Successfully complie traj_conv but running mmaction/ops/trajectory_conv_package/gradcheck.py failed.

Traceback (most recent call last):
  File "gradcheck.py", line 27, in <module>
    test = gradcheck(conv_offset3d, (input, offset), eps=1e-5, atol=1e-1, rtol=1e-5)
  File "xxx/python3.6/site-packages/torch/autograd/gradcheck.py", line 214, in gradcheck
    'numerical:%s\nanalytical:%s\n' % (i, j, n, a))
  File "xxx/python3.6/site-packages/torch/autograd/gradcheck.py", line 194, in fail_test
    raise RuntimeError(msg)
RuntimeError: Jacobian mismatch for output 0 with respect to input 1,
numerical:tensor([[0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        ...,
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.]], dtype=torch.float64)
analytical:tensor([[0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        ...,
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.],
        [0., 0., 0.,  ..., 0., 0., 0.]], dtype=torch.float64)

The following is the log when i ran the command:
cmake -DCMAKE_BUILD_TYPE=Release -DWITH_CUDA=ON -DOPENCV_EXTRA_MODULES_PATH=../../opencv_contrib-4.1.0/modules/ -DWITH_TBB=ON -DBUILD_opencv_cnn_3dobj=OFF -DBUILD_opencv_dnn=OFF -DBUILD_opencv_dnn_modern=OFF -DBUILD_opencv_dnns_easily_fooled=OFF ..

Please let me know if there is any problem in general & particularly at the bolded lines...

-- Looking for ccache - found (/home/sparsh/anaconda3/envs/venv/bin/ccache)
-- Found ZLIB: /usr/lib/x86_64-linux-gnu/libz.so (found suitable version "1.2.11", minimum required is "1.2.3")
-- Could NOT find Jasper (missing: JASPER_LIBRARIES JASPER_INCLUDE_DIR) (tried sudo apt-get install jasper. but didnt fix the problem)
-- Found ZLIB: /usr/lib/x86_64-linux-gnu/libz.so (found version "1.2.11")
-- Found OpenEXR: /usr/lib/x86_64-linux-gnu/libIlmImf.so
-- Found TBB (env): /usr/lib/x86_64-linux-gnu/libtbb.so
-- found Intel IPP (ICV version): 2019.0.0 [2019.0.0 Gold]
-- at: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/3rdparty/ippicv/ippicv_lnx/icv
-- found Intel IPP Integration Wrappers sources: 2019.0.0
-- at: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/3rdparty/ippicv/ippicv_lnx/iw
-- CUDA detected: 9.1
-- CUDA NVCC target flags: -gencode;arch=compute_30,code=sm_30;-gencode;arch=compute_35,code=sm_35;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-D_FORCE_INLINES
-- LAPACK(Atlas): LAPACK_LIBRARIES: /usr/lib/x86_64-linux-gnu/liblapack.so;/usr/lib/x86_64-linux-gnu/libcblas.so;/usr/lib/x86_64-linux-gnu/libatlas.so
-- LAPACK(Atlas): Support is enabled.
-- VTK support is disabled. Compilation of the sample code has failed. (Installed vtk module in the virtual env i'm using in anaconda. But, still the problem persists)
-- OpenCV Python: during development append to PYTHONPATH: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/python_loader
-- Caffe: NO
-- Protobuf: NO (should these be worried about?)
-- Glog: YES
-- freetype2: YES
-- harfbuzz: YES
-- HDF5: Using hdf5 compiler wrapper to determine C configuration
-- Module opencv_ovis disabled because OGRE3D was not found (No help by googling the error)
-- No preference for use of exported gflags CMake configuration set, and no hints for include/library directories provided. Defaulting to preferring an installed/exported gflags CMake configuration if available.
-- Found installed version of gflags: /home/sparsh/anaconda3/envs/venv/lib/cmake/gflags
-- Detected gflags version: 2.2.2
CMake Warning at /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/CMakeFiles/CMakeTmp/CMakeLists.txt:17 (add_executable):
Cannot generate a safe runtime search path for target cmTC_e8fd2 because
files in some directories may conflict with libraries in implicit
directories:

runtime library [libglog.so.0] in /usr/lib/x86_64-linux-gnu may be hidden by files in:
/home/sparsh/anaconda3/envs/venv/lib

Some of these libraries may not be found correctly.

-- Checking SFM deps... TRUE
-- Module opencv_sfm disabled because the following dependencies are not found: Eigen
-- Module opencv_dnn_objdetect disabled because opencv_dnn dependency can't be resolved!
-- Module opencv_text disabled because opencv_dnn dependency can't be resolved!
-- HDF5: Using hdf5 compiler wrapper to determine C configuration
-- freetype2: YES
-- harfbuzz: YES

-- General configuration for OpenCV 4.1.0 =====================================
-- Version control: unknown

-- Extra modules:
-- Location (extra): /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv_contrib-4.1.0/modules
-- Version control (extra): unknown

-- Platform:
-- Timestamp: 2019-07-16T15:06:58Z
-- Host: Linux 4.18.0-25-generic x86_64
-- CMake: 3.10.2
-- CMake generator: Unix Makefiles
-- CMake build tool: /usr/bin/make
-- Configuration: Release

-- CPU/HW features:
-- Baseline: SSE SSE2 SSE3
-- requested: SSE3
-- Dispatched code generation: SSE4_1 SSE4_2 FP16 AVX AVX2 AVX512_SKX
-- requested: SSE4_1 SSE4_2 AVX FP16 AVX2 AVX512_SKX
-- SSE4_1 (15 files): + SSSE3 SSE4_1
-- SSE4_2 (2 files): + SSSE3 SSE4_1 POPCNT SSE4_2
-- FP16 (1 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 AVX
-- AVX (4 files): + SSSE3 SSE4_1 POPCNT SSE4_2 AVX
-- AVX2 (28 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2
-- AVX512_SKX (1 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2 AVX_512F AVX512_SKX

-- C/C++:
-- Built as dynamic libs?: YES
-- C++ Compiler: /usr/bin/c++ (ver 7.4.0)
-- C++ flags (Release): -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Winit-self -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -O3 -DNDEBUG -DNDEBUG
-- C++ flags (Debug): -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Winit-self -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -g -O0 -DDEBUG -D_DEBUG
-- C Compiler: /usr/bin/cc
-- C flags (Release): -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Winit-self -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -DNDEBUG -DNDEBUG
-- C flags (Debug): -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Winit-self -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -g -O0 -DDEBUG -D_DEBUG
-- Linker flags (Release): -Wl,--gc-sections
-- Linker flags (Debug): -Wl,--gc-sections
-- ccache: YES
-- Precompiled headers: NO
-- Extra dependencies: m pthread cudart_static -lpthread dl rt nppc nppial nppicc nppicom nppidei nppif nppig nppim nppist nppisu nppitc npps cublas cufft -L/usr/lib/x86_64-linux-gnu
-- 3rdparty dependencies:

-- OpenCV modules:
-- To be built: aruco bgsegm bioinspired calib3d ccalib core cudaarithm cudabgsegm cudacodec cudafeatures2d cudafilters cudaimgproc cudalegacy cudaobjdetect cudaoptflow cudastereo cudawarping cudev datasets dpm face features2d flann freetype fuzzy gapi hdf hfs highgui img_hash imgcodecs imgproc line_descriptor ml objdetect optflow phase_unwrapping photo plot quality reg rgbd saliency shape stereo stitching structured_light superres surface_matching tracking ts video videoio videostab xfeatures2d ximgproc xobjdetect xphoto
-- Disabled: dnn world
-- Disabled by dependency: dnn_objdetect text
-- Unavailable: cnn_3dobj cvv java js matlab ovis python2 python3 sfm viz
-- Applications: tests perf_tests apps
-- Documentation: NO
-- Non-free algorithms: NO

-- GUI:
-- GTK+: YES (ver 3.22.30)
-- GThread : YES (ver 2.56.4)
-- GtkGlExt: NO
-- VTK support: NO (######Should these be worried about?######)

-- Media I/O:
-- ZLib: /usr/lib/x86_64-linux-gnu/libz.so (ver 1.2.11)
-- JPEG: /usr/lib/x86_64-linux-gnu/libjpeg.so (ver 80)
-- WEBP: /usr/lib/x86_64-linux-gnu/libwebp.so (ver encoder: 0x020e)
-- PNG: /usr/lib/x86_64-linux-gnu/libpng.so (ver 1.6.34)
-- TIFF: /usr/lib/x86_64-linux-gnu/libtiff.so (ver 42 / 4.0.9)
-- JPEG 2000: build (ver 1.900.1)
-- OpenEXR: /usr/lib/x86_64-linux-gnu/libImath.so /usr/lib/x86_64-linux-gnu/libIlmImf.so /usr/lib/x86_64-linux-gnu/libIex.so /usr/lib/x86_64-linux-gnu/libHalf.so /usr/lib/x86_64-linux-gnu/libIlmThread.so (ver 2.2.0)
-- HDR: YES
-- SUNRASTER: YES
-- PXM: YES
-- PFM: YES

-- Video I/O:
-- DC1394: YES (2.2.5)
-- FFMPEG: YES
-- avcodec: YES (57.107.100)
-- avformat: YES (57.83.100)
-- avutil: YES (55.78.100)
-- swscale: YES (4.8.100)
-- avresample: YES (3.7.0)
-- GStreamer: YES (1.14.4)
-- v4l/v4l2: YES (linux/videodev2.h)

-- Parallel framework: TBB (ver 2017.0 interface 9107)

-- Trace: YES (with Intel ITT)

-- Other third-party libraries:
-- Intel IPP: 2019.0.0 Gold [2019.0.0]
-- at: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/3rdparty/ippicv/ippicv_lnx/icv
-- Intel IPP IW: sources (2019.0.0)
-- at: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build/3rdparty/ippicv/ippicv_lnx/iw
-- Lapack: YES (/usr/lib/x86_64-linux-gnu/liblapack.so /usr/lib/x86_64-linux-gnu/libcblas.so /usr/lib/x86_64-linux-gnu/libatlas.so)
-- Eigen: NO
-- Custom HAL: NO
-- Protobuf: build (3.5.1)

-- NVIDIA CUDA: YES (ver 9.1, CUFFT CUBLAS NVCUVID)
-- NVIDIA GPU arch: 30 35 37 50 52 60 61 70
-- NVIDIA PTX archs:

-- OpenCL: YES (no extra features)
-- Include path: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/3rdparty/include/opencl/1.2
-- Link libraries: Dynamic load

-- Python (for build): /usr/bin/python2.7

-- Java:
-- ant: NO (######Should this be worried about?######)
-- JNI: /home/sparsh/anaconda3/envs/venv/include /home/sparsh/anaconda3/envs/venv/include/linux /home/sparsh/anaconda3/envs/venv/include
-- Java wrappers: NO
-- Java tests: NO (######Should these be worried about?######)

-- Install to: /usr/local

-- Configuring done
-- Generating done
-- Build files have been written to: /media/HDD_2TB/sparsh/mmaction-master/third_party/opencv-4.1.0/build

the step for Build dense_flow is not complete
after mkdir build && cd build what should i do?
i cannot do make -j
can you please explain.
Thank

Traceback (most recent call last):
File "./tools/train_localizer.py", line 90, in
main()
File "./tools/train_localizer.py", line 86, in main
logger=logger)
File "/home/z/action_detection/mmaction/mmaction/apis/train.py", line 57, in train_network
_dist_train(model, dataset, cfg, validate=validate)
File "/home/z/action_detection/mmaction/mmaction/apis/train.py", line 102, in _dist_train
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/mmcv/runner/runner.py", line 358, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/mmcv/runner/runner.py", line 260, in train
for i, data_batch in enumerate(data_loader):
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 582, in next
return self._process_next_batch(batch)
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/z/anaconda3/envs/mmaction/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/z/action_detection/mmaction/mmaction/datasets/ssn_dataset.py", line 459, in getitem
return self.prepare_train_imgs(idx)
File "/home/z/action_detection/mmaction/mmaction/datasets/ssn_dataset.py", line 635, in prepare_train_imgs
(reg_targets[1] - self.reg_stats[0][1]) /
IndexError: tuple index out of range

My folder structure is as follows:
mmaction
├── mmaction
├── tools
├── configs
├── data
│ ├── thumos14
│ │ ├── thumos14_tag_val_normalized_proposal_list.txt
│ │ ├── thumos14_tag_test_normalized_proposal_list.txt
│ │ ├── annotations_val
│ │ ├── annotations_test
│ │ ├── rawframes
│ │ │ ├── video_validation_0000001
| │ │ │ ├── img_00001.jpg
| │ │ │ ├── img_00002.jpg
| │ │ │ ├── ...
| │ │ │ ├── flow_x_00001.jpg
| │ │ │ ├── flow_x_00002.jpg
| │ │ │ ├── ...
| │ │ │ ├── flow_y_00001.jpg
| │ │ │ ├── flow_y_00002.jpg
| │ │ │ ├── ...
│ │ │ ├── ...
│ │ │ ├── video_test_0000001

hi, I found file faster_rcnn.py in models, I wonder whether mmaction can support faster-rcnn now?
If support, is there any configs can be provided, i really do not know how to construct self.train_cfg.rpn. thank you.

Hi, I was using decord to load videos from Kinetics400 but the below error occurred.

[08:31:57] /home/shwancha/mmaction/third_party/decord/src/video/video_reader.cc:145: Video Reader width: 454 is not aligned with CPU alignment preference, causing non-compact array with degraded performance. Automatically round up resolution to: 464 x 261
terminate called after throwing an instance of 'dmlc::Error'
  what():  [08:31:57] /home/shwancha/mmaction/third_party/decord/src/video/ffmpeg/ffmpeg_common.h:192: Check failed: p->linesize[0] % p->width == 0 AVFrame data is not a compact array. linesize: 1440 width: 464

Stack trace returned 10 entries:
[bt] (0) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(dmlc::StackTrace[abi:cxx11](unsigned long)+0x9d) [0x7f2eab46aefa]
[bt] (1) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x2f) [0x7f2eab46b223]
[bt] (2) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(decord::ffmpeg::ToDLTensor(std::shared_ptr<AVFrame>, DLTensor&, long*)+0x253) [0x7f2eab4d1c8f]
[bt] (3) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(decord::ffmpeg::AsNDArray(std::shared_ptr<AVFrame>)+0xc5) [0x7f2eab4d200f]
[bt] (4) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(decord::ffmpeg::FFMPEGThreadedDecoder::ProcessFrame(std::shared_ptr<AVFrame>, decord::runtime::NDArray)+0x2bf) [0x7f2eab4d100f]
[bt] (5) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(decord::ffmpeg::FFMPEGThreadedDecoder::WorkerThread()+0x50d) [0x7f2eab4d172f]
[bt] (6) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(void std::_Mem_fn_base<void (decord::ffmpeg::FFMPEGThreadedDecoder::*)(), true>::operator()<, void>(decord::ffmpeg::FFMPEGThreadedDecoder*) const+0x65) [0x7f2eab4db283]
[bt] (7) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(void std::_Bind_simple<std::_Mem_fn<void (decord::ffmpeg::FFMPEGThreadedDecoder::*)()> (decord::ffmpeg::FFMPEGThreadedDecoder*)>::_M_invoke<0ul>(std::_Index_tuple<0ul>)+0x43) [0x7f2eab4db217]
[bt] (8) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(std::_Bind_simple<std::_Mem_fn<void (decord::ffmpeg::FFMPEGThreadedDecoder::*)()> (decord::ffmpeg::FFMPEGThreadedDecoder*)>::operator()()+0x2c) [0x7f2eab4db110]
[bt] (9) /usr/local/lib/python3.6/site-packages/decord-0.0.1-py3.6.egg/decord/libdecord.so(std::thread::_Impl<std::_Bind_simple<std::_Mem_fn<void (decord::ffmpeg::FFMPEGThreadedDecoder::*)()> (decord::ffmpeg::FFMPEGThreadedDecoder*)> >::_M_run()+0x1c) [0x7f2eab4db02a]


Aborted (core dumped)

Does this mean that I have fix the resolution that is aligned with CPU alignment preference?

Hi,
Thanks for your awesome work. I train the ucf101 dataset with option '--validate' but do not see the validate log.Can you help me to figure out this problem.this is my train log.

missing keys in source state_dict: inception_4c_double_3x3_2_bn.num_batches_tracked, inception_3b_3x3_reduce_bn.num_batches_tracked, inception_4d_pool_proj_bn.num_batches_tracked, inception_3a_1x1_bn.num_batches_tracked, inception_3b_double_3x3_2_bn.num_batches_tracked, inception_3c_3x3_bn.num_batches_tracked, inception_4b_double_3x3_reduce_bn.num_batches_tracked, inception_3b_3x3_bn.num_batches_tracked, inception_4d_3x3_bn.num_batches_tracked, conv2_3x3_bn.num_batches_tracked, inception_4a_1x1_bn.num_batches_tracked, inception_5b_double_3x3_1_bn.num_batches_tracked, inception_5a_3x3_bn.num_batches_tracked, inception_4d_double_3x3_2_bn.num_batches_tracked, inception_5a_1x1_bn.num_batches_tracked, inception_5b_double_3x3_2_bn.num_batches_tracked, inception_4e_double_3x3_1_bn.num_batches_tracked, conv1_7x7_s2_bn.num_batches_tracked, inception_5b_pool_proj_bn.num_batches_tracked, inception_4c_3x3_bn.num_batches_tracked, inception_4e_double_3x3_2_bn.num_batches_tracked, inception_5a_double_3x3_2_bn.num_batches_tracked, inception_4a_double_3x3_2_bn.num_batches_tracked, inception_4e_double_3x3_reduce_bn.num_batches_tracked, inception_4a_double_3x3_reduce_bn.num_batches_tracked, inception_3b_double_3x3_1_bn.num_batches_tracked, inception_3c_3x3_reduce_bn.num_batches_tracked, inception_3b_pool_proj_bn.num_batches_tracked, inception_3a_double_3x3_2_bn.num_batches_tracked, inception_4b_double_3x3_2_bn.num_batches_tracked, inception_3a_double_3x3_reduce_bn.num_batches_tracked, inception_5b_1x1_bn.num_batches_tracked, inception_4e_3x3_reduce_bn.num_batches_tracked, inception_5b_3x3_reduce_bn.num_batches_tracked, inception_4a_3x3_reduce_bn.num_batches_tracked, inception_3c_double_3x3_1_bn.num_batches_tracked, inception_4b_3x3_reduce_bn.num_batches_tracked, inception_4d_double_3x3_reduce_bn.num_batches_tracked, inception_4e_3x3_bn.num_batches_tracked, inception_4a_3x3_bn.num_batches_tracked, inception_4b_pool_proj_bn.num_batches_tracked, inception_3c_double_3x3_reduce_bn.num_batches_tracked, inception_4c_1x1_bn.num_batches_tracked, inception_3a_pool_proj_bn.num_batches_tracked, conv2_3x3_reduce_bn.num_batches_tracked, inception_4d_1x1_bn.num_batches_tracked, inception_3b_1x1_bn.num_batches_tracked, inception_5b_3x3_bn.num_batches_tracked, inception_3a_3x3_bn.num_batches_tracked, inception_4c_double_3x3_1_bn.num_batches_tracked, inception_3a_double_3x3_1_bn.num_batches_tracked, inception_3a_3x3_reduce_bn.num_batches_tracked, inception_4b_3x3_bn.num_batches_tracked, inception_5a_double_3x3_reduce_bn.num_batches_tracked, inception_4d_double_3x3_1_bn.num_batches_tracked, inception_5a_pool_proj_bn.num_batches_tracked, inception_5a_3x3_reduce_bn.num_batches_tracked, inception_4b_1x1_bn.num_batches_tracked, inception_4a_double_3x3_1_bn.num_batches_tracked, inception_4c_double_3x3_reduce_bn.num_batches_tracked, inception_4b_double_3x3_1_bn.num_batches_tracked, inception_5a_double_3x3_1_bn.num_batches_tracked, inception_4d_3x3_reduce_bn.num_batches_tracked, inception_5b_double_3x3_reduce_bn.num_batches_tracked, inception_4c_3x3_reduce_bn.num_batches_tracked, inception_4a_pool_proj_bn.num_batches_tracked, inception_4c_pool_proj_bn.num_batches_tracked, inception_3b_double_3x3_reduce_bn.num_batches_tracked, inception_3c_double_3x3_2_bn.num_batches_tracked

2019-07-11 16:01:08,595 - INFO - Start running, host: shtf@pc, work_dir: /home/shtf/PycharmProjects/mmaction/tools/work_dirs/tsn_2d_rgb_bninception_seg_3_f1s1_b32_g8
2019-07-11 16:01:08,595 - INFO - workflow: [('train', 1)], max: 80 epochs
2019-07-11 16:01:14,603 - INFO - Epoch [1][20/299] lr: 0.00100, eta: 1:59:38, time: 0.300, data_time: 0.023, memory: 4231, loss_cls: 4.4832, loss: 4.4832
2019-07-11 16:01:20,565 - INFO - Epoch [1][40/299] lr: 0.00100, eta: 1:59:05, time: 0.298, data_time: 0.009, memory: 4231, loss_cls: 4.1506, loss: 4.1506
2019-07-11 16:01:26,599 - INFO - Epoch [1][60/299] lr: 0.00100, eta: 1:59:19, time: 0.302, data_time: 0.009, memory: 4231, loss_cls: 3.7941, loss: 3.7941
2019-07-11 16:01:32,395 - INFO - Epoch [1][80/299] lr: 0.00100, eta: 1:58:12, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 3.4967, loss: 3.4967
2019-07-11 16:01:38,171 - INFO - Epoch [1][100/299] lr: 0.00100, eta: 1:57:24, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 3.4089, loss: 3.4089
2019-07-11 16:01:43,810 - INFO - Epoch [1][120/299] lr: 0.00100, eta: 1:56:24, time: 0.282, data_time: 0.009, memory: 4231, loss_cls: 3.3399, loss: 3.3399
2019-07-11 16:01:49,456 - INFO - Epoch [1][140/299] lr: 0.00100, eta: 1:55:40, time: 0.282, data_time: 0.009, memory: 4231, loss_cls: 3.3083, loss: 3.3083
2019-07-11 16:01:55,106 - INFO - Epoch [1][160/299] lr: 0.00100, eta: 1:55:06, time: 0.282, data_time: 0.009, memory: 4231, loss_cls: 3.1467, loss: 3.1467
2019-07-11 16:02:00,795 - INFO - Epoch [1][180/299] lr: 0.00100, eta: 1:54:44, time: 0.284, data_time: 0.009, memory: 4231, loss_cls: 3.0887, loss: 3.0887
2019-07-11 16:02:06,429 - INFO - Epoch [1][200/299] lr: 0.00100, eta: 1:54:18, time: 0.282, data_time: 0.009, memory: 4231, loss_cls: 3.0245, loss: 3.0245
2019-07-11 16:02:12,073 - INFO - Epoch [1][220/299] lr: 0.00100, eta: 1:53:58, time: 0.282, data_time: 0.009, memory: 4231, loss_cls: 2.8690, loss: 2.8690
2019-07-11 16:02:17,754 - INFO - Epoch [1][240/299] lr: 0.00100, eta: 1:53:43, time: 0.284, data_time: 0.009, memory: 4231, loss_cls: 2.9678, loss: 2.9678
2019-07-11 16:02:23,407 - INFO - Epoch [1][260/299] lr: 0.00100, eta: 1:53:27, time: 0.283, data_time: 0.009, memory: 4231, loss_cls: 2.9011, loss: 2.9011
2019-07-11 16:02:29,088 - INFO - Epoch [1][280/299] lr: 0.00100, eta: 1:53:15, time: 0.284, data_time: 0.009, memory: 4231, loss_cls: 2.8469, loss: 2.8469
2019-07-11 16:02:40,882 - INFO - Epoch [2][20/299] lr: 0.00100, eta: 1:46:49, time: 0.307, data_time: 0.022, memory: 4231, loss_cls: 2.4835, loss: 2.4835
2019-07-11 16:02:46,607 - INFO - Epoch [2][40/299] lr: 0.00100, eta: 1:47:04, time: 0.286, data_time: 0.009, memory: 4231, loss_cls: 2.5342, loss: 2.5342
2019-07-11 16:02:52,373 - INFO - Epoch [2][60/299] lr: 0.00100, eta: 1:47:19, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 2.3688, loss: 2.3688
2019-07-11 16:02:58,331 - INFO - Epoch [2][80/299] lr: 0.00100, eta: 1:47:44, time: 0.298, data_time: 0.009, memory: 4231, loss_cls: 2.2748, loss: 2.2748
2019-07-11 16:03:04,129 - INFO - Epoch [2][100/299] lr: 0.00100, eta: 1:47:57, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 2.3435, loss: 2.3435
2019-07-11 16:03:09,951 - INFO - Epoch [2][120/299] lr: 0.00100, eta: 1:48:09, time: 0.291, data_time: 0.009, memory: 4231, loss_cls: 2.2911, loss: 2.2911
2019-07-11 16:03:15,876 - INFO - Epoch [2][140/299] lr: 0.00100, eta: 1:48:25, time: 0.296, data_time: 0.009, memory: 4231, loss_cls: 2.2418, loss: 2.2418
2019-07-11 16:03:21,697 - INFO - Epoch [2][160/299] lr: 0.00100, eta: 1:48:34, time: 0.291, data_time: 0.009, memory: 4231, loss_cls: 2.2246, loss: 2.2246
2019-07-11 16:03:27,545 - INFO - Epoch [2][180/299] lr: 0.00100, eta: 1:48:43, time: 0.292, data_time: 0.009, memory: 4231, loss_cls: 2.1850, loss: 2.1850
2019-07-11 16:03:33,342 - INFO - Epoch [2][200/299] lr: 0.00100, eta: 1:48:48, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 2.1686, loss: 2.1686
2019-07-11 16:03:39,162 - INFO - Epoch [2][220/299] lr: 0.00100, eta: 1:48:53, time: 0.291, data_time: 0.009, memory: 4231, loss_cls: 2.3508, loss: 2.3508
2019-07-11 16:03:44,907 - INFO - Epoch [2][240/299] lr: 0.00100, eta: 1:48:55, time: 0.287, data_time: 0.009, memory: 4231, loss_cls: 2.0961, loss: 2.0961
2019-07-11 16:03:50,672 - INFO - Epoch [2][260/299] lr: 0.00100, eta: 1:48:57, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 2.2584, loss: 2.2584
2019-07-11 16:03:56,472 - INFO - Epoch [2][280/299] lr: 0.00100, eta: 1:48:59, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 2.0572, loss: 2.0572
2019-07-11 16:04:08,384 - INFO - Epoch [3][20/299] lr: 0.00100, eta: 1:45:56, time: 0.317, data_time: 0.023, memory: 4231, loss_cls: 1.9067, loss: 1.9067
2019-07-11 16:04:14,213 - INFO - Epoch [3][40/299] lr: 0.00100, eta: 1:46:04, time: 0.291, data_time: 0.009, memory: 4231, loss_cls: 1.8512, loss: 1.8512
2019-07-11 16:04:20,044 - INFO - Epoch [3][60/299] lr: 0.00100, eta: 1:46:11, time: 0.292, data_time: 0.009, memory: 4231, loss_cls: 1.8204, loss: 1.8204
2019-07-11 16:04:25,937 - INFO - Epoch [3][80/299] lr: 0.00100, eta: 1:46:20, time: 0.295, data_time: 0.009, memory: 4231, loss_cls: 1.9100, loss: 1.9100
2019-07-11 16:04:31,668 - INFO - Epoch [3][100/299] lr: 0.00100, eta: 1:46:22, time: 0.287, data_time: 0.009, memory: 4231, loss_cls: 1.8866, loss: 1.8866
2019-07-11 16:04:37,450 - INFO - Epoch [3][120/299] lr: 0.00100, eta: 1:46:26, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.9218, loss: 1.9218
2019-07-11 16:04:43,197 - INFO - Epoch [3][140/299] lr: 0.00100, eta: 1:46:28, time: 0.287, data_time: 0.009, memory: 4231, loss_cls: 1.9288, loss: 1.9288
2019-07-11 16:04:48,966 - INFO - Epoch [3][160/299] lr: 0.00100, eta: 1:46:31, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 1.8066, loss: 1.8066
2019-07-11 16:04:54,957 - INFO - Epoch [3][180/299] lr: 0.00100, eta: 1:46:39, time: 0.300, data_time: 0.009, memory: 4231, loss_cls: 1.8147, loss: 1.8147
2019-07-11 16:05:01,236 - INFO - Epoch [3][200/299] lr: 0.00100, eta: 1:46:55, time: 0.314, data_time: 0.009, memory: 4231, loss_cls: 1.7075, loss: 1.7075
2019-07-11 16:05:07,022 - INFO - Epoch [3][220/299] lr: 0.00100, eta: 1:46:56, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.6702, loss: 1.6702
2019-07-11 16:05:13,038 - INFO - Epoch [3][240/299] lr: 0.00100, eta: 1:47:04, time: 0.301, data_time: 0.009, memory: 4231, loss_cls: 1.6549, loss: 1.6549
2019-07-11 16:05:19,190 - INFO - Epoch [3][260/299] lr: 0.00100, eta: 1:47:14, time: 0.308, data_time: 0.009, memory: 4231, loss_cls: 1.6716, loss: 1.6716
2019-07-11 16:05:25,126 - INFO - Epoch [3][280/299] lr: 0.00100, eta: 1:47:17, time: 0.297, data_time: 0.009, memory: 4231, loss_cls: 1.6736, loss: 1.6736
2019-07-11 16:05:37,129 - INFO - Epoch [4][20/299] lr: 0.00100, eta: 1:45:12, time: 0.317, data_time: 0.023, memory: 4231, loss_cls: 1.6452, loss: 1.6452
2019-07-11 16:05:42,879 - INFO - Epoch [4][40/299] lr: 0.00100, eta: 1:45:13, time: 0.287, data_time: 0.009, memory: 4231, loss_cls: 1.5390, loss: 1.5390
2019-07-11 16:05:48,644 - INFO - Epoch [4][60/299] lr: 0.00100, eta: 1:45:14, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 1.5590, loss: 1.5590
2019-07-11 16:05:54,548 - INFO - Epoch [4][80/299] lr: 0.00100, eta: 1:45:18, time: 0.295, data_time: 0.009, memory: 4231, loss_cls: 1.5566, loss: 1.5566
2019-07-11 16:06:00,341 - INFO - Epoch [4][100/299] lr: 0.00100, eta: 1:45:19, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 1.6053, loss: 1.6053
2019-07-11 16:06:06,444 - INFO - Epoch [4][120/299] lr: 0.00100, eta: 1:45:27, time: 0.305, data_time: 0.010, memory: 4231, loss_cls: 1.5732, loss: 1.5732
2019-07-11 16:06:12,791 - INFO - Epoch [4][140/299] lr: 0.00100, eta: 1:45:39, time: 0.317, data_time: 0.009, memory: 4231, loss_cls: 1.5011, loss: 1.5011
2019-07-11 16:06:18,803 - INFO - Epoch [4][160/299] lr: 0.00100, eta: 1:45:44, time: 0.301, data_time: 0.010, memory: 4231, loss_cls: 1.7146, loss: 1.7146
2019-07-11 16:06:24,903 - INFO - Epoch [4][180/299] lr: 0.00100, eta: 1:45:50, time: 0.305, data_time: 0.009, memory: 4231, loss_cls: 1.5631, loss: 1.5631
2019-07-11 16:06:30,684 - INFO - Epoch [4][200/299] lr: 0.00100, eta: 1:45:49, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.5973, loss: 1.5973
2019-07-11 16:06:36,566 - INFO - Epoch [4][220/299] lr: 0.00100, eta: 1:45:50, time: 0.294, data_time: 0.011, memory: 4231, loss_cls: 1.5032, loss: 1.5032
2019-07-11 16:06:42,559 - INFO - Epoch [4][240/299] lr: 0.00100, eta: 1:45:53, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 1.5111, loss: 1.5111
2019-07-11 16:06:48,338 - INFO - Epoch [4][260/299] lr: 0.00100, eta: 1:45:51, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.6058, loss: 1.6058
2019-07-11 16:06:54,351 - INFO - Epoch [4][280/299] lr: 0.00100, eta: 1:45:54, time: 0.301, data_time: 0.009, memory: 4231, loss_cls: 1.5886, loss: 1.5886
2019-07-11 16:07:06,101 - INFO - Epoch [5][20/299] lr: 0.00100, eta: 1:44:15, time: 0.308, data_time: 0.023, memory: 4231, loss_cls: 1.2971, loss: 1.2971
2019-07-11 16:07:11,848 - INFO - Epoch [5][40/299] lr: 0.00100, eta: 1:44:14, time: 0.287, data_time: 0.009, memory: 4231, loss_cls: 1.2731, loss: 1.2731
2019-07-11 16:07:17,711 - INFO - Epoch [5][60/299] lr: 0.00100, eta: 1:44:14, time: 0.293, data_time: 0.009, memory: 4231, loss_cls: 1.3834, loss: 1.3834
2019-07-11 16:07:23,478 - INFO - Epoch [5][80/299] lr: 0.00100, eta: 1:44:13, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 1.1701, loss: 1.1701
2019-07-11 16:07:29,229 - INFO - Epoch [5][100/299] lr: 0.00100, eta: 1:44:12, time: 0.288, data_time: 0.009, memory: 4231, loss_cls: 1.4695, loss: 1.4695
2019-07-11 16:07:35,164 - INFO - Epoch [5][120/299] lr: 0.00100, eta: 1:44:13, time: 0.297, data_time: 0.009, memory: 4231, loss_cls: 1.4136, loss: 1.4136
2019-07-11 16:07:40,946 - INFO - Epoch [5][140/299] lr: 0.00100, eta: 1:44:12, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.3309, loss: 1.3309
2019-07-11 16:07:46,752 - INFO - Epoch [5][160/299] lr: 0.00100, eta: 1:44:11, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 1.3232, loss: 1.3232
2019-07-11 16:07:52,651 - INFO - Epoch [5][180/299] lr: 0.00100, eta: 1:44:11, time: 0.295, data_time: 0.011, memory: 4231, loss_cls: 1.2392, loss: 1.2392
2019-07-11 16:07:58,494 - INFO - Epoch [5][200/299] lr: 0.00100, eta: 1:44:10, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 1.3366, loss: 1.3366
2019-07-11 16:08:04,262 - INFO - Epoch [5][220/299] lr: 0.00100, eta: 1:44:08, time: 0.288, data_time: 0.010, memory: 4231, loss_cls: 1.2811, loss: 1.2811
2019-07-11 16:08:10,034 - INFO - Epoch [5][240/299] lr: 0.00100, eta: 1:44:06, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.2721, loss: 1.2721
2019-07-11 16:08:15,855 - INFO - Epoch [5][260/299] lr: 0.00100, eta: 1:44:05, time: 0.291, data_time: 0.009, memory: 4231, loss_cls: 1.4750, loss: 1.4750
2019-07-11 16:08:21,693 - INFO - Epoch [5][280/299] lr: 0.00100, eta: 1:44:03, time: 0.292, data_time: 0.009, memory: 4231, loss_cls: 1.3883, loss: 1.3883
2019-07-11 16:08:33,349 - INFO - Epoch [6][20/299] lr: 0.00100, eta: 1:42:42, time: 0.305, data_time: 0.023, memory: 4231, loss_cls: 1.2580, loss: 1.2580
2019-07-11 16:08:39,199 - INFO - Epoch [6][40/299] lr: 0.00100, eta: 1:42:42, time: 0.293, data_time: 0.011, memory: 4231, loss_cls: 1.1847, loss: 1.1847
2019-07-11 16:08:44,970 - INFO - Epoch [6][60/299] lr: 0.00100, eta: 1:42:40, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 1.2383, loss: 1.2383
2019-07-11 16:08:50,777 - INFO - Epoch [6][80/299] lr: 0.00100, eta: 1:42:39, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 1.1851, loss: 1.1851
2019-07-11 16:08:56,612 - INFO - Epoch [6][100/299] lr: 0.00100, eta: 1:42:38, time: 0.292, data_time: 0.011, memory: 4231, loss_cls: 1.1629, loss: 1.1629
2019-07-11 16:09:02,432 - INFO - Epoch [6][120/299] lr: 0.00100, eta: 1:42:36, time: 0.291, data_time: 0.010, memory: 4231, loss_cls: 1.2775, loss: 1.2775
2019-07-11 16:09:08,428 - INFO - Epoch [6][140/299] lr: 0.00100, eta: 1:42:37, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 1.2151, loss: 1.2151
2019-07-11 16:09:14,456 - INFO - Epoch [6][160/299] lr: 0.00100, eta: 1:42:39, time: 0.302, data_time: 0.009, memory: 4231, loss_cls: 1.1899, loss: 1.1899
2019-07-11 16:09:20,859 - INFO - Epoch [6][180/299] lr: 0.00100, eta: 1:42:45, time: 0.320, data_time: 0.010, memory: 4231, loss_cls: 1.2422, loss: 1.2422
2019-07-11 16:09:27,057 - INFO - Epoch [6][200/299] lr: 0.00100, eta: 1:42:48, time: 0.310, data_time: 0.012, memory: 4231, loss_cls: 1.2231, loss: 1.2231
2019-07-11 16:09:32,977 - INFO - Epoch [6][220/299] lr: 0.00100, eta: 1:42:47, time: 0.296, data_time: 0.010, memory: 4231, loss_cls: 1.2336, loss: 1.2336
2019-07-11 16:09:38,785 - INFO - Epoch [6][240/299] lr: 0.00100, eta: 1:42:45, time: 0.290, data_time: 0.009, memory: 4231, loss_cls: 1.0611, loss: 1.0611
2019-07-11 16:09:44,983 - INFO - Epoch [6][260/299] lr: 0.00100, eta: 1:42:47, time: 0.310, data_time: 0.009, memory: 4231, loss_cls: 1.1490, loss: 1.1490
2019-07-11 16:09:51,317 - INFO - Epoch [6][280/299] lr: 0.00100, eta: 1:42:51, time: 0.317, data_time: 0.010, memory: 4231, loss_cls: 1.1411, loss: 1.1411
2019-07-11 16:10:03,719 - INFO - Epoch [7][20/299] lr: 0.00100, eta: 1:41:43, time: 0.310, data_time: 0.028, memory: 4231, loss_cls: 1.0960, loss: 1.0960
2019-07-11 16:10:09,526 - INFO - Epoch [7][40/299] lr: 0.00100, eta: 1:41:41, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 1.0871, loss: 1.0871
2019-07-11 16:10:15,332 - INFO - Epoch [7][60/299] lr: 0.00100, eta: 1:41:39, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 1.0862, loss: 1.0862
2019-07-11 16:10:21,486 - INFO - Epoch [7][80/299] lr: 0.00100, eta: 1:41:41, time: 0.308, data_time: 0.010, memory: 4231, loss_cls: 1.0366, loss: 1.0366
2019-07-11 16:10:27,719 - INFO - Epoch [7][100/299] lr: 0.00100, eta: 1:41:44, time: 0.312, data_time: 0.011, memory: 4231, loss_cls: 1.1492, loss: 1.1492
2019-07-11 16:10:34,087 - INFO - Epoch [7][120/299] lr: 0.00100, eta: 1:41:48, time: 0.318, data_time: 0.011, memory: 4231, loss_cls: 1.0891, loss: 1.0891
2019-07-11 16:10:40,455 - INFO - Epoch [7][140/299] lr: 0.00100, eta: 1:41:51, time: 0.318, data_time: 0.010, memory: 4231, loss_cls: 1.0713, loss: 1.0713
2019-07-11 16:10:47,001 - INFO - Epoch [7][160/299] lr: 0.00100, eta: 1:41:57, time: 0.327, data_time: 0.011, memory: 4231, loss_cls: 1.0720, loss: 1.0720
2019-07-11 16:10:53,466 - INFO - Epoch [7][180/299] lr: 0.00100, eta: 1:42:01, time: 0.323, data_time: 0.011, memory: 4231, loss_cls: 0.9987, loss: 0.9987
2019-07-11 16:10:59,636 - INFO - Epoch [7][200/299] lr: 0.00100, eta: 1:42:02, time: 0.308, data_time: 0.010, memory: 4231, loss_cls: 1.0794, loss: 1.0794
2019-07-11 16:11:05,432 - INFO - Epoch [7][220/299] lr: 0.00100, eta: 1:41:59, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 1.0925, loss: 1.0925
2019-07-11 16:11:11,272 - INFO - Epoch [7][240/299] lr: 0.00100, eta: 1:41:56, time: 0.292, data_time: 0.011, memory: 4231, loss_cls: 1.1454, loss: 1.1454
2019-07-11 16:11:17,132 - INFO - Epoch [7][260/299] lr: 0.00100, eta: 1:41:53, time: 0.293, data_time: 0.011, memory: 4231, loss_cls: 1.1134, loss: 1.1134
2019-07-11 16:11:23,076 - INFO - Epoch [7][280/299] lr: 0.00100, eta: 1:41:51, time: 0.297, data_time: 0.010, memory: 4231, loss_cls: 0.8931, loss: 0.8931
2019-07-11 16:11:35,629 - INFO - Epoch [8][20/299] lr: 0.00100, eta: 1:40:54, time: 0.323, data_time: 0.027, memory: 4231, loss_cls: 0.9906, loss: 0.9906
2019-07-11 16:11:41,472 - INFO - Epoch [8][40/299] lr: 0.00100, eta: 1:40:52, time: 0.292, data_time: 0.009, memory: 4231, loss_cls: 0.9621, loss: 0.9621
2019-07-11 16:11:47,581 - INFO - Epoch [8][60/299] lr: 0.00100, eta: 1:40:52, time: 0.305, data_time: 0.011, memory: 4231, loss_cls: 0.9577, loss: 0.9577
2019-07-11 16:11:53,510 - INFO - Epoch [8][80/299] lr: 0.00100, eta: 1:40:50, time: 0.296, data_time: 0.011, memory: 4231, loss_cls: 0.9554, loss: 0.9554
2019-07-11 16:11:59,890 - INFO - Epoch [8][100/299] lr: 0.00100, eta: 1:40:53, time: 0.319, data_time: 0.010, memory: 4231, loss_cls: 0.9889, loss: 0.9889
2019-07-11 16:12:06,383 - INFO - Epoch [8][120/299] lr: 0.00100, eta: 1:40:56, time: 0.325, data_time: 0.010, memory: 4231, loss_cls: 1.0829, loss: 1.0829
2019-07-11 16:12:12,628 - INFO - Epoch [8][140/299] lr: 0.00100, eta: 1:40:57, time: 0.312, data_time: 0.010, memory: 4231, loss_cls: 1.1398, loss: 1.1398
2019-07-11 16:12:18,518 - INFO - Epoch [8][160/299] lr: 0.00100, eta: 1:40:54, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 1.1582, loss: 1.1582
2019-07-11 16:12:24,516 - INFO - Epoch [8][180/299] lr: 0.00100, eta: 1:40:52, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 1.0249, loss: 1.0249
2019-07-11 16:12:30,488 - INFO - Epoch [8][200/299] lr: 0.00100, eta: 1:40:50, time: 0.299, data_time: 0.009, memory: 4231, loss_cls: 0.8630, loss: 0.8630
2019-07-11 16:12:36,581 - INFO - Epoch [8][220/299] lr: 0.00100, eta: 1:40:50, time: 0.305, data_time: 0.010, memory: 4231, loss_cls: 0.8933, loss: 0.8933
2019-07-11 16:12:42,903 - INFO - Epoch [8][240/299] lr: 0.00100, eta: 1:40:51, time: 0.316, data_time: 0.010, memory: 4231, loss_cls: 0.9473, loss: 0.9473
2019-07-11 16:12:49,042 - INFO - Epoch [8][260/299] lr: 0.00100, eta: 1:40:50, time: 0.307, data_time: 0.012, memory: 4231, loss_cls: 0.9556, loss: 0.9556
2019-07-11 16:12:55,201 - INFO - Epoch [8][280/299] lr: 0.00100, eta: 1:40:49, time: 0.308, data_time: 0.010, memory: 4231, loss_cls: 1.0438, loss: 1.0438
2019-07-11 16:13:07,343 - INFO - Epoch [9][20/299] lr: 0.00100, eta: 1:39:55, time: 0.306, data_time: 0.024, memory: 4231, loss_cls: 0.9604, loss: 0.9604
2019-07-11 16:13:13,128 - INFO - Epoch [9][40/299] lr: 0.00100, eta: 1:39:51, time: 0.289, data_time: 0.010, memory: 4231, loss_cls: 0.8427, loss: 0.8427
2019-07-11 16:13:18,920 - INFO - Epoch [9][60/299] lr: 0.00100, eta: 1:39:48, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 0.8564, loss: 0.8564
2019-07-11 16:13:24,702 - INFO - Epoch [9][80/299] lr: 0.00100, eta: 1:39:44, time: 0.289, data_time: 0.009, memory: 4231, loss_cls: 0.9623, loss: 0.9623
2019-07-11 16:13:30,484 - INFO - Epoch [9][100/299] lr: 0.00100, eta: 1:39:40, time: 0.289, data_time: 0.010, memory: 4231, loss_cls: 1.0100, loss: 1.0100
2019-07-11 16:13:36,291 - INFO - Epoch [9][120/299] lr: 0.00100, eta: 1:39:36, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 0.9493, loss: 0.9493
2019-07-11 16:13:42,161 - INFO - Epoch [9][140/299] lr: 0.00100, eta: 1:39:33, time: 0.294, data_time: 0.012, memory: 4231, loss_cls: 0.9082, loss: 0.9082
2019-07-11 16:13:48,039 - INFO - Epoch [9][160/299] lr: 0.00100, eta: 1:39:30, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 0.8538, loss: 0.8538
2019-07-11 16:13:53,843 - INFO - Epoch [9][180/299] lr: 0.00100, eta: 1:39:26, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 0.8293, loss: 0.8293
2019-07-11 16:13:59,697 - INFO - Epoch [9][200/299] lr: 0.00100, eta: 1:39:23, time: 0.293, data_time: 0.011, memory: 4231, loss_cls: 0.8396, loss: 0.8396
2019-07-11 16:14:05,571 - INFO - Epoch [9][220/299] lr: 0.00100, eta: 1:39:20, time: 0.294, data_time: 0.011, memory: 4231, loss_cls: 0.8043, loss: 0.8043
2019-07-11 16:14:11,405 - INFO - Epoch [9][240/299] lr: 0.00100, eta: 1:39:16, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.8688, loss: 0.8688
2019-07-11 16:14:17,250 - INFO - Epoch [9][260/299] lr: 0.00100, eta: 1:39:12, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.8506, loss: 0.8506
2019-07-11 16:14:23,128 - INFO - Epoch [9][280/299] lr: 0.00100, eta: 1:39:09, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 0.7565, loss: 0.7565
2019-07-11 16:14:35,041 - INFO - Epoch [10][20/299] lr: 0.00100, eta: 1:38:21, time: 0.308, data_time: 0.025, memory: 4231, loss_cls: 0.7351, loss: 0.7351
2019-07-11 16:14:41,003 - INFO - Epoch [10][40/299] lr: 0.00100, eta: 1:38:18, time: 0.298, data_time: 0.011, memory: 4231, loss_cls: 0.8406, loss: 0.8406
2019-07-11 16:14:46,910 - INFO - Epoch [10][60/299] lr: 0.00100, eta: 1:38:15, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.8138, loss: 0.8138
2019-07-11 16:14:52,861 - INFO - Epoch [10][80/299] lr: 0.00100, eta: 1:38:13, time: 0.298, data_time: 0.010, memory: 4231, loss_cls: 0.8658, loss: 0.8658
2019-07-11 16:14:59,051 - INFO - Epoch [10][100/299] lr: 0.00100, eta: 1:38:12, time: 0.309, data_time: 0.011, memory: 4231, loss_cls: 0.9357, loss: 0.9357
2019-07-11 16:15:05,110 - INFO - Epoch [10][120/299] lr: 0.00100, eta: 1:38:10, time: 0.303, data_time: 0.010, memory: 4231, loss_cls: 0.9362, loss: 0.9362
2019-07-11 16:15:11,309 - INFO - Epoch [10][140/299] lr: 0.00100, eta: 1:38:09, time: 0.310, data_time: 0.011, memory: 4231, loss_cls: 0.7638, loss: 0.7638
2019-07-11 16:15:17,648 - INFO - Epoch [10][160/299] lr: 0.00100, eta: 1:38:09, time: 0.317, data_time: 0.010, memory: 4231, loss_cls: 0.7723, loss: 0.7723
2019-07-11 16:15:23,521 - INFO - Epoch [10][180/299] lr: 0.00100, eta: 1:38:05, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 0.8819, loss: 0.8819
2019-07-11 16:15:29,732 - INFO - Epoch [10][200/299] lr: 0.00100, eta: 1:38:04, time: 0.311, data_time: 0.010, memory: 4231, loss_cls: 0.8365, loss: 0.8365
2019-07-11 16:15:35,609 - INFO - Epoch [10][220/299] lr: 0.00100, eta: 1:38:01, time: 0.294, data_time: 0.011, memory: 4231, loss_cls: 0.8349, loss: 0.8349
2019-07-11 16:15:41,514 - INFO - Epoch [10][240/299] lr: 0.00100, eta: 1:37:57, time: 0.295, data_time: 0.011, memory: 4231, loss_cls: 0.8983, loss: 0.8983
2019-07-11 16:15:47,357 - INFO - Epoch [10][260/299] lr: 0.00100, eta: 1:37:53, time: 0.292, data_time: 0.009, memory: 4231, loss_cls: 0.8890, loss: 0.8890
2019-07-11 16:15:53,223 - INFO - Epoch [10][280/299] lr: 0.00100, eta: 1:37:50, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.8605, loss: 0.8605
2019-07-11 16:16:05,190 - INFO - Epoch [11][20/299] lr: 0.00100, eta: 1:37:06, time: 0.311, data_time: 0.025, memory: 4231, loss_cls: 0.7940, loss: 0.7940
2019-07-11 16:16:11,173 - INFO - Epoch [11][40/299] lr: 0.00100, eta: 1:37:03, time: 0.299, data_time: 0.010, memory: 4231, loss_cls: 0.7823, loss: 0.7823
2019-07-11 16:16:17,663 - INFO - Epoch [11][60/299] lr: 0.00100, eta: 1:37:04, time: 0.324, data_time: 0.011, memory: 4231, loss_cls: 0.9363, loss: 0.9363
2019-07-11 16:16:24,002 - INFO - Epoch [11][80/299] lr: 0.00100, eta: 1:37:04, time: 0.317, data_time: 0.011, memory: 4231, loss_cls: 0.6983, loss: 0.6983
2019-07-11 16:16:29,910 - INFO - Epoch [11][100/299] lr: 0.00100, eta: 1:37:00, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.8656, loss: 0.8656
2019-07-11 16:16:35,756 - INFO - Epoch [11][120/299] lr: 0.00100, eta: 1:36:56, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.7612, loss: 0.7612
2019-07-11 16:16:41,675 - INFO - Epoch [11][140/299] lr: 0.00100, eta: 1:36:53, time: 0.296, data_time: 0.011, memory: 4231, loss_cls: 0.7202, loss: 0.7202
2019-07-11 16:16:47,580 - INFO - Epoch [11][160/299] lr: 0.00100, eta: 1:36:49, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.6902, loss: 0.6902
2019-07-11 16:16:53,623 - INFO - Epoch [11][180/299] lr: 0.00100, eta: 1:36:47, time: 0.302, data_time: 0.010, memory: 4231, loss_cls: 0.7435, loss: 0.7435
2019-07-11 16:16:59,467 - INFO - Epoch [11][200/299] lr: 0.00100, eta: 1:36:43, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.7949, loss: 0.7949
2019-07-11 16:17:05,375 - INFO - Epoch [11][220/299] lr: 0.00100, eta: 1:36:39, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.6952, loss: 0.6952
2019-07-11 16:17:11,268 - INFO - Epoch [11][240/299] lr: 0.00100, eta: 1:36:35, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.7068, loss: 0.7068
2019-07-11 16:17:17,212 - INFO - Epoch [11][260/299] lr: 0.00100, eta: 1:36:32, time: 0.297, data_time: 0.010, memory: 4231, loss_cls: 0.7871, loss: 0.7871
2019-07-11 16:17:23,455 - INFO - Epoch [11][280/299] lr: 0.00100, eta: 1:36:30, time: 0.312, data_time: 0.010, memory: 4231, loss_cls: 0.7040, loss: 0.7040
2019-07-11 16:17:35,377 - INFO - Epoch [12][20/299] lr: 0.00100, eta: 1:35:50, time: 0.308, data_time: 0.023, memory: 4231, loss_cls: 0.7366, loss: 0.7366
2019-07-11 16:17:41,377 - INFO - Epoch [12][40/299] lr: 0.00100, eta: 1:35:47, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 0.7067, loss: 0.7067
2019-07-11 16:17:47,225 - INFO - Epoch [12][60/299] lr: 0.00100, eta: 1:35:43, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.7746, loss: 0.7746
2019-07-11 16:17:53,165 - INFO - Epoch [12][80/299] lr: 0.00100, eta: 1:35:39, time: 0.297, data_time: 0.011, memory: 4231, loss_cls: 0.7293, loss: 0.7293
2019-07-11 16:17:59,022 - INFO - Epoch [12][100/299] lr: 0.00100, eta: 1:35:35, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.6752, loss: 0.6752
2019-07-11 16:18:04,917 - INFO - Epoch [12][120/299] lr: 0.00100, eta: 1:35:32, time: 0.295, data_time: 0.010, memory: 4231, loss_cls: 0.7532, loss: 0.7532
2019-07-11 16:18:10,886 - INFO - Epoch [12][140/299] lr: 0.00100, eta: 1:35:28, time: 0.298, data_time: 0.011, memory: 4231, loss_cls: 0.7927, loss: 0.7927
2019-07-11 16:18:16,799 - INFO - Epoch [12][160/299] lr: 0.00100, eta: 1:35:25, time: 0.296, data_time: 0.011, memory: 4231, loss_cls: 0.6452, loss: 0.6452
2019-07-11 16:18:23,013 - INFO - Epoch [12][180/299] lr: 0.00100, eta: 1:35:23, time: 0.311, data_time: 0.010, memory: 4231, loss_cls: 0.7257, loss: 0.7257
2019-07-11 16:18:28,949 - INFO - Epoch [12][200/299] lr: 0.00100, eta: 1:35:19, time: 0.297, data_time: 0.010, memory: 4231, loss_cls: 0.6688, loss: 0.6688
2019-07-11 16:18:35,839 - INFO - Epoch [12][220/299] lr: 0.00100, eta: 1:35:21, time: 0.344, data_time: 0.010, memory: 4231, loss_cls: 0.7529, loss: 0.7529
2019-07-11 16:18:41,854 - INFO - Epoch [12][240/299] lr: 0.00100, eta: 1:35:18, time: 0.301, data_time: 0.010, memory: 4231, loss_cls: 0.6159, loss: 0.6159
2019-07-11 16:18:47,919 - INFO - Epoch [12][260/299] lr: 0.00100, eta: 1:35:15, time: 0.303, data_time: 0.010, memory: 4231, loss_cls: 0.7416, loss: 0.7416
2019-07-11 16:18:53,989 - INFO - Epoch [12][280/299] lr: 0.00100, eta: 1:35:12, time: 0.303, data_time: 0.010, memory: 4231, loss_cls: 0.6462, loss: 0.6462
2019-07-11 16:19:06,196 - INFO - Epoch [13][20/299] lr: 0.00100, eta: 1:34:36, time: 0.323, data_time: 0.025, memory: 4231, loss_cls: 0.7296, loss: 0.7296
2019-07-11 16:19:12,199 - INFO - Epoch [13][40/299] lr: 0.00100, eta: 1:34:32, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 0.6721, loss: 0.6721
2019-07-11 16:19:18,034 - INFO - Epoch [13][60/299] lr: 0.00100, eta: 1:34:28, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.6665, loss: 0.6665
2019-07-11 16:19:24,069 - INFO - Epoch [13][80/299] lr: 0.00100, eta: 1:34:25, time: 0.302, data_time: 0.012, memory: 4231, loss_cls: 0.8136, loss: 0.8136
2019-07-11 16:19:30,198 - INFO - Epoch [13][100/299] lr: 0.00100, eta: 1:34:22, time: 0.306, data_time: 0.010, memory: 4231, loss_cls: 0.6294, loss: 0.6294
2019-07-11 16:19:36,050 - INFO - Epoch [13][120/299] lr: 0.00100, eta: 1:34:18, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.6746, loss: 0.6746
2019-07-11 16:19:41,961 - INFO - Epoch [13][140/299] lr: 0.00100, eta: 1:34:14, time: 0.296, data_time: 0.010, memory: 4231, loss_cls: 0.6621, loss: 0.6621
2019-07-11 16:19:47,917 - INFO - Epoch [13][160/299] lr: 0.00100, eta: 1:34:10, time: 0.298, data_time: 0.011, memory: 4231, loss_cls: 0.7160, loss: 0.7160
2019-07-11 16:19:53,816 - INFO - Epoch [13][180/299] lr: 0.00100, eta: 1:34:06, time: 0.295, data_time: 0.011, memory: 4231, loss_cls: 0.6304, loss: 0.6304
2019-07-11 16:19:59,635 - INFO - Epoch [13][200/299] lr: 0.00100, eta: 1:34:02, time: 0.291, data_time: 0.010, memory: 4231, loss_cls: 0.7408, loss: 0.7408
2019-07-11 16:20:05,491 - INFO - Epoch [13][220/299] lr: 0.00100, eta: 1:33:58, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.6236, loss: 0.6236
2019-07-11 16:20:11,456 - INFO - Epoch [13][240/299] lr: 0.00100, eta: 1:33:54, time: 0.298, data_time: 0.012, memory: 4231, loss_cls: 0.5930, loss: 0.5930
2019-07-11 16:20:17,333 - INFO - Epoch [13][260/299] lr: 0.00100, eta: 1:33:50, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 0.6186, loss: 0.6186
2019-07-11 16:20:23,231 - INFO - Epoch [13][280/299] lr: 0.00100, eta: 1:33:46, time: 0.295, data_time: 0.011, memory: 4231, loss_cls: 0.7483, loss: 0.7483
2019-07-11 16:20:35,119 - INFO - Epoch [14][20/299] lr: 0.00100, eta: 1:33:10, time: 0.310, data_time: 0.024, memory: 4231, loss_cls: 0.5920, loss: 0.5920
2019-07-11 16:20:41,076 - INFO - Epoch [14][40/299] lr: 0.00100, eta: 1:33:07, time: 0.298, data_time: 0.010, memory: 4231, loss_cls: 0.6214, loss: 0.6214
2019-07-11 16:20:47,221 - INFO - Epoch [14][60/299] lr: 0.00100, eta: 1:33:04, time: 0.307, data_time: 0.010, memory: 4231, loss_cls: 0.6059, loss: 0.6059
2019-07-11 16:20:53,268 - INFO - Epoch [14][80/299] lr: 0.00100, eta: 1:33:01, time: 0.302, data_time: 0.011, memory: 4231, loss_cls: 0.6120, loss: 0.6120
2019-07-11 16:20:59,458 - INFO - Epoch [14][100/299] lr: 0.00100, eta: 1:32:58, time: 0.309, data_time: 0.011, memory: 4231, loss_cls: 0.5707, loss: 0.5707
2019-07-11 16:21:05,434 - INFO - Epoch [14][120/299] lr: 0.00100, eta: 1:32:54, time: 0.299, data_time: 0.010, memory: 4231, loss_cls: 0.7148, loss: 0.7148
2019-07-11 16:21:11,506 - INFO - Epoch [14][140/299] lr: 0.00100, eta: 1:32:51, time: 0.304, data_time: 0.011, memory: 4231, loss_cls: 0.5862, loss: 0.5862
2019-07-11 16:21:17,625 - INFO - Epoch [14][160/299] lr: 0.00100, eta: 1:32:48, time: 0.306, data_time: 0.011, memory: 4231, loss_cls: 0.6053, loss: 0.6053
2019-07-11 16:21:23,448 - INFO - Epoch [14][180/299] lr: 0.00100, eta: 1:32:43, time: 0.291, data_time: 0.010, memory: 4231, loss_cls: 0.6400, loss: 0.6400
2019-07-11 16:21:29,262 - INFO - Epoch [14][200/299] lr: 0.00100, eta: 1:32:39, time: 0.291, data_time: 0.010, memory: 4231, loss_cls: 0.6415, loss: 0.6415
2019-07-11 16:21:35,131 - INFO - Epoch [14][220/299] lr: 0.00100, eta: 1:32:34, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.5485, loss: 0.5485
2019-07-11 16:21:41,716 - INFO - Epoch [14][240/299] lr: 0.00100, eta: 1:32:33, time: 0.329, data_time: 0.010, memory: 4231, loss_cls: 0.5219, loss: 0.5219
2019-07-11 16:21:47,573 - INFO - Epoch [14][260/299] lr: 0.00100, eta: 1:32:29, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.6286, loss: 0.6286
2019-07-11 16:21:53,383 - INFO - Epoch [14][280/299] lr: 0.00100, eta: 1:32:24, time: 0.290, data_time: 0.010, memory: 4231, loss_cls: 0.5689, loss: 0.5689
2019-07-11 16:22:05,558 - INFO - Epoch [15][20/299] lr: 0.00100, eta: 1:31:53, time: 0.326, data_time: 0.025, memory: 4231, loss_cls: 0.5249, loss: 0.5249
2019-07-11 16:22:11,472 - INFO - Epoch [15][40/299] lr: 0.00100, eta: 1:31:49, time: 0.296, data_time: 0.010, memory: 4231, loss_cls: 0.6768, loss: 0.6768
2019-07-11 16:22:17,351 - INFO - Epoch [15][60/299] lr: 0.00100, eta: 1:31:44, time: 0.294, data_time: 0.010, memory: 4231, loss_cls: 0.6489, loss: 0.6489
2019-07-11 16:22:23,180 - INFO - Epoch [15][80/299] lr: 0.00100, eta: 1:31:40, time: 0.291, data_time: 0.010, memory: 4231, loss_cls: 0.5200, loss: 0.5200
2019-07-11 16:22:29,125 - INFO - Epoch [15][100/299] lr: 0.00100, eta: 1:31:36, time: 0.297, data_time: 0.012, memory: 4231, loss_cls: 0.5926, loss: 0.5926
2019-07-11 16:22:35,082 - INFO - Epoch [15][120/299] lr: 0.00100, eta: 1:31:32, time: 0.298, data_time: 0.011, memory: 4231, loss_cls: 0.5289, loss: 0.5289
2019-07-11 16:22:41,070 - INFO - Epoch [15][140/299] lr: 0.00100, eta: 1:31:28, time: 0.299, data_time: 0.011, memory: 4231, loss_cls: 0.5145, loss: 0.5145
2019-07-11 16:22:46,997 - INFO - Epoch [15][160/299] lr: 0.00100, eta: 1:31:24, time: 0.296, data_time: 0.010, memory: 4231, loss_cls: 0.5401, loss: 0.5401
2019-07-11 16:22:53,147 - INFO - Epoch [15][180/299] lr: 0.00100, eta: 1:31:21, time: 0.307, data_time: 0.010, memory: 4231, loss_cls: 0.6155, loss: 0.6155
2019-07-11 16:22:59,546 - INFO - Epoch [15][200/299] lr: 0.00100, eta: 1:31:19, time: 0.320, data_time: 0.011, memory: 4231, loss_cls: 0.5247, loss: 0.5247
2019-07-11 16:23:05,486 - INFO - Epoch [15][220/299] lr: 0.00100, eta: 1:31:14, time: 0.297, data_time: 0.011, memory: 4231, loss_cls: 0.6124, loss: 0.6124
2019-07-11 16:23:11,510 - INFO - Epoch [15][240/299] lr: 0.00100, eta: 1:31:11, time: 0.301, data_time: 0.010, memory: 4231, loss_cls: 0.6230, loss: 0.6230
2019-07-11 16:23:17,447 - INFO - Epoch [15][260/299] lr: 0.00100, eta: 1:31:06, time: 0.297, data_time: 0.010, memory: 4231, loss_cls: 0.5985, loss: 0.5985
2019-07-11 16:23:23,366 - INFO - Epoch [15][280/299] lr: 0.00100, eta: 1:31:02, time: 0.296, data_time: 0.011, memory: 4231, loss_cls: 0.5207, loss: 0.5207
2019-07-11 16:23:35,508 - INFO - Epoch [16][20/299] lr: 0.00100, eta: 1:30:31, time: 0.316, data_time: 0.024, memory: 4231, loss_cls: 0.5657, loss: 0.5657
2019-07-11 16:23:41,646 - INFO - Epoch [16][40/299] lr: 0.00100, eta: 1:30:28, time: 0.307, data_time: 0.010, memory: 4231, loss_cls: 0.5757, loss: 0.5757
2019-07-11 16:23:47,492 - INFO - Epoch [16][60/299] lr: 0.00100, eta: 1:30:23, time: 0.292, data_time: 0.011, memory: 4231, loss_cls: 0.5366, loss: 0.5366
2019-07-11 16:23:53,341 - INFO - Epoch [16][80/299] lr: 0.00100, eta: 1:30:19, time: 0.292, data_time: 0.010, memory: 4231, loss_cls: 0.6070, loss: 0.6070
2019-07-11 16:23:59,531 - INFO - Epoch [16][100/299] lr: 0.00100, eta: 1:30:16, time: 0.310, data_time: 0.010, memory: 4231, loss_cls: 0.6961, loss: 0.6961
2019-07-11 16:24:05,399 - INFO - Epoch [16][120/299] lr: 0.00100, eta: 1:30:11, time: 0.293, data_time: 0.010, memory: 4231, loss_cls: 0.7001, loss: 0.7001
2019-07-11 16:24:11,390 - INFO - Epoch [16][140/299] lr: 0.00100, eta: 1:30:07, time: 0.300, data_time: 0.010, memory: 4231, loss_cls: 0.5185, loss: 0.5185
2019-07-11 16:24:17,287 - INFO - Epoch [16][160/299] lr: 0.00100, eta: 1:30:03, time: 0.295, data_time: 0.011, memory: 4231, loss_cls: 0.5651, loss: 0.5651
2019-07-11 16:24:23,417 - INFO - Epoch [16][180/299] lr: 0.00100, eta: 1:29:59, time: 0.306, data_time: 0.010, memory: 4231, loss_cls: 0.6530, loss: 0.6530
2019-07-11 16:24:29,943 - INFO - Epoch [16][200/299] lr: 0.00100, eta: 1:29:58, time: 0.326, data_time: 0.011, memory: 4231, loss_cls: 0.6232, loss: 0.6232

There's no extract_rgb_frames.bash file in data_tools/ucf101, how can I only extract RGB frames from videos?

Hi,

When I build the Decord library to install the video loader, following the steps:

cd third_party/decord
mkdir build && build
cmake .. -DUSE_CUDA=0
make

An error appears while run this command "cmake .. -DUSE_CUDA=0":

CMake Error at CMakeLists.txt:1 (cmake_minimum_required):
  CMake 3.8 or higher is required.  You are running version 3.5.1


-- Configuring incomplete, errors occurred!

But I update the CMake version, ubuntu system reminder:
cmake is already the newest version (3.5.1-1ubuntu3).

Hi, I have a problem on Kinetics action recognition training. Since I don't have enough storage space, I decide to go for video dataloader training. The command line I am using is:

./tools/dist_train_recognizer.sh configs/kinetics400/i3d_kinetics400_3d_rgb_r50_c3d_inflate3x1x1_seg1_f32s2_video.py 8 --validate

There is no error, but the training is extremely slow. Like below, it needs 132 days to finish training.

2019-07-05 18:28:14,206 - INFO - workflow: [('train', 1)], max: 100 epochs
2019-07-05 18:38:44,201 - INFO - Epoch [1][20/3637]     lr: 0.01000, eta: 132 days, 14:08:21, time: 31.499, data_time: 11.109, memory: 5219, loss_cls: 6.0129, loss: 6.0129

I think I installed everything, I don't know why this happens. My suspicious is on video dataloader or some setting issues. Do you have any suggestions/ideas how to fix this? Thank you very much.

I see some steps got updated for densflow.
can you tell me how should i make densflow now.
it gives me the error
make: *** No targets specified and no makefile found. Stop.
when I do make -j

The following is the command & the errors that followed:

NOTE:
The missing keys all have ".num_batches_tracked" in common.

sparsh/mmaction-master$ python tools/test_recognizer.py configs/ucf101/tsn_rgb_bninception.py modelzoo/tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth
Downloading: "https://open-mmlab.s3.ap-northeast-2.amazonaws.com/pretrain/third_party/bn_inception_caffe-ed2e8665.pth" to /home/sparsh/.cache/torch/checkpoints/bn_inception_caffe-ed2e8665.pth
100.0%
unexpected key in source state_dict: fc.weight, fc.bias

missing keys in source state_dict: inception_4b_pool_proj_bn.num_batches_tracked, inception_5a_3x3_reduce_bn.num_batches_tracked, inception_4c_pool_proj_bn.num_batches_tracked, inception_5a_3x3_bn.num_batches_tracked, inception_4e_double_3x3_1_bn.num_batches_tracked, inception_5b_pool_proj_bn.num_batches_tracked, inception_4d_3x3_bn.num_batches_tracked, inception_3b_3x3_bn.num_batches_tracked, inception_5b_double_3x3_2_bn.num_batches_tracked, inception_4d_double_3x3_1_bn.num_batches_tracked, inception_4b_3x3_bn.num_batches_tracked, inception_5a_double_3x3_2_bn.num_batches_tracked, inception_5b_double_3x3_reduce_bn.num_batches_tracked, inception_4b_double_3x3_1_bn.num_batches_tracked, inception_4b_double_3x3_reduce_bn.num_batches_tracked, inception_4c_3x3_reduce_bn.num_batches_tracked, inception_3a_double_3x3_2_bn.num_batches_tracked, inception_5a_double_3x3_reduce_bn.num_batches_tracked, inception_3b_3x3_reduce_bn.num_batches_tracked, inception_5b_3x3_bn.num_batches_tracked, inception_5b_double_3x3_1_bn.num_batches_tracked, inception_3a_3x3_bn.num_batches_tracked, inception_4a_3x3_reduce_bn.num_batches_tracked, inception_3c_double_3x3_2_bn.num_batches_tracked, conv2_3x3_reduce_bn.num_batches_tracked, conv1_7x7_s2_bn.num_batches_tracked, inception_4c_double_3x3_reduce_bn.num_batches_tracked, inception_4c_double_3x3_1_bn.num_batches_tracked, inception_4d_double_3x3_2_bn.num_batches_tracked, inception_3b_1x1_bn.num_batches_tracked, inception_3c_double_3x3_1_bn.num_batches_tracked, inception_4a_double_3x3_2_bn.num_batches_tracked, inception_3b_double_3x3_2_bn.num_batches_tracked, inception_5a_1x1_bn.num_batches_tracked, inception_4c_1x1_bn.num_batches_tracked, inception_4c_3x3_bn.num_batches_tracked, inception_5b_3x3_reduce_bn.num_batches_tracked, inception_5a_pool_proj_bn.num_batches_tracked, inception_3b_pool_proj_bn.num_batches_tracked, inception_3b_double_3x3_1_bn.num_batches_tracked, inception_4c_double_3x3_2_bn.num_batches_tracked, inception_4b_double_3x3_2_bn.num_batches_tracked, inception_3a_double_3x3_1_bn.num_batches_tracked, inception_3a_1x1_bn.num_batches_tracked, inception_4a_1x1_bn.num_batches_tracked, inception_3a_pool_proj_bn.num_batches_tracked, inception_4a_double_3x3_1_bn.num_batches_tracked, inception_4b_1x1_bn.num_batches_tracked, inception_3c_3x3_bn.num_batches_tracked, inception_4d_1x1_bn.num_batches_tracked, inception_4e_3x3_bn.num_batches_tracked, inception_4d_double_3x3_reduce_bn.num_batches_tracked, inception_4d_3x3_reduce_bn.num_batches_tracked, inception_3c_double_3x3_reduce_bn.num_batches_tracked, inception_3a_3x3_reduce_bn.num_batches_tracked, inception_3b_double_3x3_reduce_bn.num_batches_tracked, inception_5a_double_3x3_1_bn.num_batches_tracked, inception_4e_double_3x3_2_bn.num_batches_tracked, inception_4a_3x3_bn.num_batches_tracked, inception_4e_double_3x3_reduce_bn.num_batches_tracked, conv2_3x3_bn.num_batches_tracked, inception_4e_3x3_reduce_bn.num_batches_tracked, inception_3c_3x3_reduce_bn.num_batches_tracked, inception_5b_1x1_bn.num_batches_tracked, inception_4a_pool_proj_bn.num_batches_tracked, inception_4b_3x3_reduce_bn.num_batches_tracked, inception_4d_pool_proj_bn.num_batches_tracked, inception_3a_double_3x3_reduce_bn.num_batches_tracked, inception_4a_double_3x3_reduce_bn.num_batches_tracked

[>>>>> ] 423/3783, 0.8 task/s, elapsed: 535s, ETA: 4246sTraceback (most recent call last):

File "tools/test_recognizer.py", line 122, in
main()
File "tools/test_recognizer.py", line 83, in main
outputs = single_test(model, data_loader)
File "tools/test_recognizer.py", line 20, in single_test
for i, data in enumerate(data_loader):
File "/home/sparsh/anaconda3/envs/venv/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 568, in next
return self._process_next_batch(batch)
File "/home/sparsh/anaconda3/envs/venv/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/sparsh/anaconda3/envs/venv/lib/python3.5/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/sparsh/anaconda3/envs/venv/lib/python3.5/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/media/Seagate_4TB2/sparsh/mmaction-master/mmaction/datasets/rawframes_dataset.py", line 271, in getitem
gt_label=DC(to_tensor(record.label), stack=True,
File "/media/Seagate_4TB2/sparsh/mmaction-master/mmaction/datasets/rawframes_dataset.py", line 25, in label
return int(self._data[2])
IndexError: list index out of range

Hi I am wordering how to install the NCCV package? Thank you

I tried to apply parallel test but this error occurred:
_pickle.PicklingError: Can't pickle <function _data_func at 0x7fe56fa76510>: attribute lookup _data_func on main failed
@zhaoyue-zephyrus

Hi, I have build opencv 4.1.0 with cuda 9.2 and I have build the latest available dense_flow repository. I am extracting flow frames for my own video dataset using the build_rawframes.py script. However it is taking a lot of time even on GPU for extracting the flow frames. I have increased the number of workers for multiprocessing so that the GPU memory can be fully utilized. But I want to extract the frames for 4000 videos and with this speed it may take a long time, is it the usual speed ? Please let me know , thank you very much for the code.

When I click it, just return the 404NotFond, Please check it.
Other pretrained models can be downloaded.
Thany you!

I followed the exact step of install.md, but error occurs when I do the "make" operation

when I prepare to test the inference, I got this error

I checked all the Requirements except decord and dense_flow. I saw thay are optional then did not build these two.
Could you tell me why this happen? How to solve this?
Thank you!

Tasks

• Video classificaiton
  • 2D CNN (RGB, Two-stream CNN)
  • 3D CNN (I3D)
  • TSN sampling
• Temporal Action Detection
  • SSN
  • TAG proposal (v0.2)
  • BSN proposal (v0.2)
• Spatial Temporal Action Detection (bounding box only)
  • Fast R-CNN + I3D
• Generic Data Interfaces (v0.1.1)

Demos (v0.1.1)

• Video classification
• Temporal action detection
• Spatial temporal detection (bounding box only)

New Operators

• Trajectory Convolution
• 2D Correlection (v0.1.1)
• 3D ROIPool (v0.2)

Dataset

• UCF101
• Kinetics-400
• SomethingSomething-V1
• THUMOS14
• AVA
• ActivityNet
• Custom Dataset
• Charades (v0.2)
• Epic-Kitchen (v0.2)

Documentation

• README
• Dataset Preparation
• Getting started guide
• Extension guide
• Model zoo
• Contributing
• License

Model Zoo

• Model files
• Download links
  • AWS S3
  • AliCloud

shichen@shichen-Inspiron-3670:~/mma/mmaction$ python tools/test_recognizer.py configs/ucf101/tsn_rgb_bninception.py tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth
[ ] 0/38, elapsed: 0s, ETA:Traceback (most recent call last):
File "tools/test_recognizer.py", line 122, in
main()
File "tools/test_recognizer.py", line 83, in main
outputs = single_test(model, data_loader)
File "tools/test_recognizer.py", line 20, in single_test
for i, data in enumerate(data_loader):
File "/home/shichen/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 582, in next
return self._process_next_batch(batch)
File "/home/shichen/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
TypeError: Traceback (most recent call last):
File "/home/shichen/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/shichen/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/shichen/mmaction-master/mmaction/datasets/rawframes_dataset.py", line 272, in getitem
pad_dims=None))
TypeError: init() got an unexpected keyword argument 'pad_dims'

Hi, thank you for your code.

when I ran 'python tools/test_recognizer.py configs/ucf101/tsn_rgb_bninception.py tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth' showed as Getting_start.md, it shows that error I pasted.

I have checked that function and there is no attributes 'pad_dims'.
Is that a bug?

Thank you. @zhaoyue-zephyrus

After installed Decord and dense_flow successful,
I ran the script:extract_frames.sh,and I got the errors ,some of the logs blew:

................
../third_party/dense_flow/build/extract_gpu: error while loading shared libraries: libcublas.so.9.1: cannot open shared object file: No such file or directory
...............

my device:
ubuntu-16.04
cuda-10.1
OpenCV 4.1.0
I download NVIDIA VIDEO CODEC SDK and copy the header files to my cuda path also.

Any help is appreciated！

I like to do temporal action detection.
Can you help on how to evaluated the existing methods on THUMOS14 dataset?
I know part of it should be like this:
python tools/test_localizer.py configs/thumos14/ssn_thumos14_rgb_bn_inception.py ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [other task-specific arguments]
but i know know the rest.
should i download {CHECKPOINT_FILE} from some other places? I download the ssn_thumos14_rgb_bn_inception_tag-dac9ddb0.pth and put that in the model zoo.

How should i set the other arguments?

Hi @zhaoyue-zephyrus !

I am trying to train & test the TSN model on NTU dataset. I am following the instructions given in dataset.md file. Say I'm able to extract frames & generated the filelist, what should I have to do further? Should I modify any of the scripts? Also, how should I prepare config files for NTU? (Can seeing the config for UCF101 & preparing a similar one for NTU suffice?)

Hi @zhaoyue-zephyrus ,

thanks for this wonderful repo.

I noticed that the --resume switch for data_tools/build_rawframes.py does not work, as the set difference operation fullpath_list = set(fullpath_list).difference(set(done_fullpath_list)) will always return the fullpath_list and not the difference between fullpath_list and done_fullpath_list. This is because, the args.src_dir and args.out_dir will most likely vary. Here is a quick fix that I used to get the fullpath_list of the rest over videos. This works well for --level=1, did not test it for --level=2.

Thanks.

    all_vid_ids = [osp.split(vid_path)[1].split('.')[0] for vid_path in fullpath_list]
    done_vid_ids = [osp.split(vid_path)[1] for vid_path in done_fullpath_list]
    todo_vid_ids = list(set(all_vid_ids).difference(set(done_vid_ids)))
    todo_fullpath_list = [args.src_dir + todo_vid_id + '.' + args.ext for todo_vid_id in todo_vid_ids]
    fullpath_list = todo_fullpath_list

Hi,
Thanks for your contribution of mmaction which is an awesome open-source project on the GitHub! I have a few questions about the performance of AVA model which is in the model zoo.
My questions are:

1. How many epochs do I need until achieving the score 21.2 by [email protected]?
2. Can I utilize the default setting file in order to achieve this score?
3. If I use default batch_size=2, then my GPU memory will be full. So I change the batch_size to 1. Should I change the learning rate etc? Because with the default setting except for the batch size, I cannot achieve 21.2 [email protected] after 12 epochs.

When I wanna test i3d model in kinetics dataset with the pretrained model you offered in Model zoo, these series of "unexpected key" problem occurred.

~/Downloads/mmaction$ python tools/test_recognizer.py configs/kinetics400/i3d_kinetics400_3d_rgb_r50_c3d_inflate3x1x1_seg1_f32s2.py modelzoo/i3d_r50_f32s2_k400-2c57e077.pth

unexpected key in source state_dict: fc.weight, fc.bias

missing keys in source state_dict: layer3.0.bn1.num_batches_tracked, layer3.3.bn1.num_batches_tracked, layer3.2.bn2.num_batches_tracked, layer3.0.bn3.num_batches_tracked, layer2.2.bn1.num_batches_tracked, layer3.2.bn3.num_batches_tracked, layer2.0.bn1.num_batches_tracked, layer2.3.bn3.num_batches_tracked, bn1.num_batches_tracked, layer4.0.bn1.num_batches_tracked, layer3.4.bn3.num_batches_tracked, layer3.5.bn2.num_batches_tracked, layer2.1.bn2.num_batches_tracked, layer4.1.bn2.num_batches_tracked, layer3.3.bn3.num_batches_tracked, layer3.2.bn1.num_batches_tracked, layer1.1.bn2.num_batches_tracked, layer1.0.bn3.num_batches_tracked, layer2.2.bn3.num_batches_tracked, layer3.1.bn3.num_batches_tracked, layer1.2.bn3.num_batches_tracked, layer2.1.bn3.num_batches_tracked, layer4.2.bn3.num_batches_tracked, layer3.0.bn2.num_batches_tracked, layer2.1.bn1.num_batches_tracked, layer3.5.bn1.num_batches_tracked, layer3.3.bn2.num_batches_tracked, layer1.2.bn2.num_batches_tracked, layer4.0.bn2.num_batches_tracked, layer3.4.bn2.num_batches_tracked, layer2.0.bn2.num_batches_tracked, layer2.0.downsample.1.num_batches_tracked, layer4.1.bn3.num_batches_tracked, layer1.1.bn1.num_batches_tracked, layer3.4.bn1.num_batches_tracked, layer2.3.bn1.num_batches_tracked, layer3.0.downsample.1.num_batches_tracked, layer1.1.bn3.num_batches_tracked, layer1.0.bn2.num_batches_tracked, layer2.3.bn2.num_batches_tracked, layer2.2.bn2.num_batches_tracked, layer4.0.downsample.1.num_batches_tracked, layer3.5.bn3.num_batches_tracked, layer3.1.bn1.num_batches_tracked, layer4.2.bn2.num_batches_tracked, layer3.1.bn2.num_batches_tracked, layer2.0.bn3.num_batches_tracked, layer1.0.downsample.1.num_batches_tracked, layer4.1.bn1.num_batches_tracked, layer4.0.bn3.num_batches_tracked, layer4.2.bn1.num_batches_tracked, layer1.0.bn1.num_batches_tracked, layer1.2.bn1.num_batches_tracked

Traceback (most recent call last):
  File "tools/test_recognizer.py", line 123, in <module>
    main()
  File "tools/test_recognizer.py", line 74, in main
    load_checkpoint(model, args.checkpoint, strict=True)
  File "/home/fourier/anaconda3/envs/pytorch/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 162, in load_checkpoint
    load_state_dict(model, state_dict, strict, logger)
  File "/home/fourier/anaconda3/envs/pytorch/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 86, in load_state_dict
    raise RuntimeError(err_msg)
RuntimeError: unexpected key in source state_dict: conv1.weight, bn1.weight, bn1.bias, bn1.running_mean, bn1.running_var, bn1.num_batches_tracked, layer1.0.conv1.weight, layer1.0.conv2.weight, layer1.0.bn1.weight, layer1.0.bn1.bias, layer1.0.bn1.running_mean, layer1.0.bn1.running_var, layer1.0.bn1.num_batches_tracked, layer1.0.bn2.weight, layer1.0.bn2.bias, layer1.0.bn2.running_mean, layer1.0.bn2.running_var, layer1.0.bn2.num_batches_tracked, layer1.0.conv3.weight, layer1.0.bn3.weight, layer1.0.bn3.bias, layer1.0.bn3.running_mean, layer1.0.bn3.running_var, layer1.0.bn3.num_batches_tracked, layer1.0.downsample.0.weight, layer1.0.downsample.1.weight, layer1.0.downsample.1.bias, layer1.0.downsample.1.running_mean, layer1.0.downsample.1.running_var, layer1.0.downsample.1.num_batches_tracked, layer1.1.conv1.weight, layer1.1.conv2.weight, layer1.1.bn1.weight, layer1.1.bn1.bias, layer1.1.bn1.running_mean, layer1.1.bn1.running_var, layer1.1.bn1.num_batches_tracked, layer1.1.bn2.weight, layer1.1.bn2.bias, layer1.1.bn2.running_mean, layer1.1.bn2.running_var, layer1.1.bn2.num_batches_tracked, layer1.1.conv3.weight, layer1.1.bn3.weight, layer1.1.bn3.bias, layer1.1.bn3.running_mean, layer1.1.bn3.running_var, layer1.1.bn3.num_batches_tracked, layer1.2.conv1.weight, layer1.2.conv2.weight, layer1.2.bn1.weight, layer1.2.bn1.bias, layer1.2.bn1.running_mean, layer1.2.bn1.running_var, layer1.2.bn1.num_batches_tracked, layer1.2.bn2.weight, layer1.2.bn2.bias, layer1.2.bn2.running_mean, layer1.2.bn2.running_var, layer1.2.bn2.num_batches_tracked, layer1.2.conv3.weight, layer1.2.bn3.weight, layer1.2.bn3.bias, layer1.2.bn3.running_mean, layer1.2.bn3.running_var, layer1.2.bn3.num_batches_tracked, layer2.0.conv1.weight, layer2.0.conv2.weight, layer2.0.bn1.weight, layer2.0.bn1.bias, layer2.0.bn1.running_mean, layer2.0.bn1.running_var, layer2.0.bn1.num_batches_tracked, layer2.0.bn2.weight, layer2.0.bn2.bias, layer2.0.bn2.running_mean, layer2.0.bn2.running_var, layer2.0.bn2.num_batches_tracked, layer2.0.conv3.weight, layer2.0.bn3.weight, layer2.0.bn3.bias, layer2.0.bn3.running_mean, layer2.0.bn3.running_var, layer2.0.bn3.num_batches_tracked, layer2.0.downsample.0.weight, layer2.0.downsample.1.weight, layer2.0.downsample.1.bias, layer2.0.downsample.1.running_mean, layer2.0.downsample.1.running_var, layer2.0.downsample.1.num_batches_tracked, layer2.1.conv1.weight, layer2.1.conv2.weight, layer2.1.bn1.weight, layer2.1.bn1.bias, layer2.1.bn1.running_mean, layer2.1.bn1.running_var, layer2.1.bn1.num_batches_tracked, layer2.1.bn2.weight, layer2.1.bn2.bias, layer2.1.bn2.running_mean, layer2.1.bn2.running_var, layer2.1.bn2.num_batches_tracked, layer2.1.conv3.weight, layer2.1.bn3.weight, layer2.1.bn3.bias, layer2.1.bn3.running_mean, layer2.1.bn3.running_var, layer2.1.bn3.num_batches_tracked, layer2.2.conv1.weight, layer2.2.conv2.weight, layer2.2.bn1.weight, layer2.2.bn1.bias, layer2.2.bn1.running_mean, layer2.2.bn1.running_var, layer2.2.bn1.num_batches_tracked, layer2.2.bn2.weight, layer2.2.bn2.bias, layer2.2.bn2.running_mean, layer2.2.bn2.running_var, layer2.2.bn2.num_batches_tracked, layer2.2.conv3.weight, layer2.2.bn3.weight, layer2.2.bn3.bias, layer2.2.bn3.running_mean, layer2.2.bn3.running_var, layer2.2.bn3.num_batches_tracked, layer2.3.conv1.weight, layer2.3.conv2.weight, layer2.3.bn1.weight, layer2.3.bn1.bias, layer2.3.bn1.running_mean, layer2.3.bn1.running_var, layer2.3.bn1.num_batches_tracked, layer2.3.bn2.weight, layer2.3.bn2.bias, layer2.3.bn2.running_mean, layer2.3.bn2.running_var, layer2.3.bn2.num_batches_tracked, layer2.3.conv3.weight, layer2.3.bn3.weight, layer2.3.bn3.bias, layer2.3.bn3.running_mean, layer2.3.bn3.running_var, layer2.3.bn3.num_batches_tracked, layer3.0.conv1.weight, layer3.0.conv2.weight, layer3.0.bn1.weight, layer3.0.bn1.bias, layer3.0.bn1.running_mean, layer3.0.bn1.running_var, layer3.0.bn1.num_batches_tracked, layer3.0.bn2.weight, layer3.0.bn2.bias, layer3.0.bn2.running_mean, layer3.0.bn2.running_var, layer3.0.bn2.num_batches_tracked, layer3.0.conv3.weight, layer3.0.bn3.weight, layer3.0.bn3.bias, layer3.0.bn3.running_mean, layer3.0.bn3.running_var, layer3.0.bn3.num_batches_tracked, layer3.0.downsample.0.weight, layer3.0.downsample.1.weight, layer3.0.downsample.1.bias, layer3.0.downsample.1.running_mean, layer3.0.downsample.1.running_var, layer3.0.downsample.1.num_batches_tracked, layer3.1.conv1.weight, layer3.1.conv2.weight, layer3.1.bn1.weight, layer3.1.bn1.bias, layer3.1.bn1.running_mean, layer3.1.bn1.running_var, layer3.1.bn1.num_batches_tracked, layer3.1.bn2.weight, layer3.1.bn2.bias, layer3.1.bn2.running_mean, layer3.1.bn2.running_var, layer3.1.bn2.num_batches_tracked, layer3.1.conv3.weight, layer3.1.bn3.weight, layer3.1.bn3.bias, layer3.1.bn3.running_mean, layer3.1.bn3.running_var, layer3.1.bn3.num_batches_tracked, layer3.2.conv1.weight, layer3.2.conv2.weight, layer3.2.bn1.weight, layer3.2.bn1.bias, layer3.2.bn1.running_mean, layer3.2.bn1.running_var, layer3.2.bn1.num_batches_tracked, layer3.2.bn2.weight, layer3.2.bn2.bias, layer3.2.bn2.running_mean, layer3.2.bn2.running_var, layer3.2.bn2.num_batches_tracked, layer3.2.conv3.weight, layer3.2.bn3.weight, layer3.2.bn3.bias, layer3.2.bn3.running_mean, layer3.2.bn3.running_var, layer3.2.bn3.num_batches_tracked, layer3.3.conv1.weight, layer3.3.conv2.weight, layer3.3.bn1.weight, layer3.3.bn1.bias, layer3.3.bn1.running_mean, layer3.3.bn1.running_var, layer3.3.bn1.num_batches_tracked, layer3.3.bn2.weight, layer3.3.bn2.bias, layer3.3.bn2.running_mean, layer3.3.bn2.running_var, layer3.3.bn2.num_batches_tracked, layer3.3.conv3.weight, layer3.3.bn3.weight, layer3.3.bn3.bias, layer3.3.bn3.running_mean, layer3.3.bn3.running_var, layer3.3.bn3.num_batches_tracked, layer3.4.conv1.weight, layer3.4.conv2.weight, layer3.4.bn1.weight, layer3.4.bn1.bias, layer3.4.bn1.running_mean, layer3.4.bn1.running_var, layer3.4.bn1.num_batches_tracked, layer3.4.bn2.weight, layer3.4.bn2.bias, layer3.4.bn2.running_mean, layer3.4.bn2.running_var, layer3.4.bn2.num_batches_tracked, layer3.4.conv3.weight, layer3.4.bn3.weight, layer3.4.bn3.bias, layer3.4.bn3.running_mean, layer3.4.bn3.running_var, layer3.4.bn3.num_batches_tracked, layer3.5.conv1.weight, layer3.5.conv2.weight, layer3.5.bn1.weight, layer3.5.bn1.bias, layer3.5.bn1.running_mean, layer3.5.bn1.running_var, layer3.5.bn1.num_batches_tracked, layer3.5.bn2.weight, layer3.5.bn2.bias, layer3.5.bn2.running_mean, layer3.5.bn2.running_var, layer3.5.bn2.num_batches_tracked, layer3.5.conv3.weight, layer3.5.bn3.weight, layer3.5.bn3.bias, layer3.5.bn3.running_mean, layer3.5.bn3.running_var, layer3.5.bn3.num_batches_tracked, layer4.0.conv1.weight, layer4.0.conv2.weight, layer4.0.bn1.weight, layer4.0.bn1.bias, layer4.0.bn1.running_mean, layer4.0.bn1.running_var, layer4.0.bn1.num_batches_tracked, layer4.0.bn2.weight, layer4.0.bn2.bias, layer4.0.bn2.running_mean, layer4.0.bn2.running_var, layer4.0.bn2.num_batches_tracked, layer4.0.conv3.weight, layer4.0.bn3.weight, layer4.0.bn3.bias, layer4.0.bn3.running_mean, layer4.0.bn3.running_var, layer4.0.bn3.num_batches_tracked, layer4.0.downsample.0.weight, layer4.0.downsample.1.weight, layer4.0.downsample.1.bias, layer4.0.downsample.1.running_mean, layer4.0.downsample.1.running_var, layer4.0.downsample.1.num_batches_tracked, layer4.1.conv1.weight, layer4.1.conv2.weight, layer4.1.bn1.weight, layer4.1.bn1.bias, layer4.1.bn1.running_mean, layer4.1.bn1.running_var, layer4.1.bn1.num_batches_tracked, layer4.1.bn2.weight, layer4.1.bn2.bias, layer4.1.bn2.running_mean, layer4.1.bn2.running_var, layer4.1.bn2.num_batches_tracked, layer4.1.conv3.weight, layer4.1.bn3.weight, layer4.1.bn3.bias, layer4.1.bn3.running_mean, layer4.1.bn3.running_var, layer4.1.bn3.num_batches_tracked, layer4.2.conv1.weight, layer4.2.conv2.weight, layer4.2.bn1.weight, layer4.2.bn1.bias, layer4.2.bn1.running_mean, layer4.2.bn1.running_var, layer4.2.bn1.num_batches_tracked, layer4.2.bn2.weight, layer4.2.bn2.bias, layer4.2.bn2.running_mean, layer4.2.bn2.running_var, layer4.2.bn2.num_batches_tracked, layer4.2.conv3.weight, layer4.2.bn3.weight, layer4.2.bn3.bias, layer4.2.bn3.running_mean, layer4.2.bn3.running_var, layer4.2.bn3.num_batches_tracked

missing keys in source state_dict: backbone.layer3.1.conv3.weight, backbone.layer2.1.bn2.bias, backbone.layer3.3.bn2.running_mean, backbone.layer1.2.conv3.weight, backbone.layer3.2.bn3.num_batches_tracked, backbone.layer3.4.bn3.weight, backbone.layer2.1.bn1.num_batches_tracked, backbone.layer3.2.bn3.running_mean, backbone.layer1.0.bn3.weight, backbone.layer2.3.conv1.weight, backbone.layer3.5.bn2.num_batches_tracked, backbone.bn1.num_batches_tracked, backbone.layer2.2.bn1.weight, backbone.layer4.0.downsample.1.weight, backbone.layer4.2.bn2.running_var, backbone.layer2.2.bn3.weight, backbone.layer3.4.bn1.weight, backbone.layer1.1.bn2.running_mean, backbone.layer3.2.bn1.weight, backbone.layer1.0.conv1.weight, backbone.layer3.0.bn2.num_batches_tracked, backbone.layer4.1.conv2.weight, backbone.layer2.3.bn2.running_mean, backbone.layer3.2.conv2.weight, backbone.layer3.0.downsample.1.num_batches_tracked, backbone.layer3.3.bn1.weight, backbone.layer1.0.bn2.running_var, backbone.layer3.5.bn2.bias, backbone.layer2.1.bn1.weight, backbone.layer1.2.bn2.num_batches_tracked, backbone.layer4.2.bn3.num_batches_tracked, backbone.layer3.3.conv3.weight, backbone.bn1.running_var, backbone.layer3.3.bn1.running_var, backbone.layer3.5.bn1.weight, backbone.layer4.1.bn2.running_mean, backbone.layer4.0.downsample.1.running_mean, backbone.layer4.1.bn1.running_var, backbone.layer3.0.bn3.running_var, backbone.layer3.0.downsample.1.running_mean, backbone.layer1.0.bn3.running_var, backbone.layer3.1.bn1.running_var, backbone.layer3.3.bn1.bias, backbone.layer1.2.bn1.num_batches_tracked, backbone.layer4.0.bn3.num_batches_tracked, backbone.layer4.1.bn1.bias, backbone.layer4.1.bn3.bias, backbone.layer2.2.conv3.weight, backbone.layer3.5.bn2.weight, backbone.layer4.0.bn2.running_mean, backbone.layer1.0.downsample.1.running_mean, backbone.layer1.1.conv2.weight, backbone.layer2.1.bn1.running_mean, backbone.layer2.3.bn2.running_var, backbone.layer4.0.bn1.weight, backbone.layer4.1.bn2.bias, backbone.layer3.2.conv3.weight, backbone.layer3.1.bn2.running_mean, backbone.layer3.2.bn1.running_var, backbone.layer2.0.downsample.1.running_var, backbone.layer2.0.bn3.running_var, backbone.layer3.0.downsample.1.weight, backbone.layer2.2.bn2.running_var, backbone.layer3.3.bn3.weight, backbone.layer1.2.bn3.running_mean, backbone.layer4.0.bn3.bias, backbone.layer4.0.downsample.1.running_var, backbone.layer3.4.bn1.bias, backbone.layer4.1.bn3.running_var, backbone.layer2.0.bn3.running_mean, backbone.layer2.0.bn2.bias, backbone.layer3.0.conv3.weight, backbone.layer3.5.conv2.weight, cls_head.fc_cls.weight, backbone.layer1.0.bn2.weight, backbone.layer2.0.downsample.1.bias, backbone.layer1.0.conv3.weight, backbone.layer3.0.conv1.weight, backbone.layer3.5.bn3.running_var, backbone.layer3.4.bn1.num_batches_tracked, backbone.layer3.1.bn3.num_batches_tracked, backbone.layer2.3.bn3.weight, backbone.layer3.5.bn2.running_mean, backbone.layer1.1.bn1.running_mean, backbone.layer2.0.conv1.weight, backbone.layer1.1.bn2.num_batches_tracked, backbone.layer2.0.bn3.bias, backbone.layer2.3.bn1.running_mean, backbone.layer2.2.bn1.running_mean, backbone.layer1.1.bn1.running_var, backbone.layer2.3.bn2.weight, backbone.layer3.5.conv1.weight, backbone.layer2.0.conv2.weight, backbone.layer1.0.downsample.1.running_var, backbone.layer4.0.conv2.weight, backbone.layer4.0.conv3.weight, backbone.layer4.1.conv1.weight, backbone.layer3.4.bn2.bias, backbone.layer4.2.conv1.weight, backbone.layer3.1.bn1.bias, backbone.layer2.2.bn2.weight, backbone.layer3.2.bn1.num_batches_tracked, backbone.bn1.weight, backbone.layer3.4.conv3.weight, backbone.layer2.2.bn1.bias, backbone.layer1.1.bn2.running_var, backbone.layer1.2.bn1.bias, backbone.layer3.1.bn2.num_batches_tracked, backbone.layer3.5.bn1.num_batches_tracked, backbone.layer4.0.bn2.num_batches_tracked, backbone.layer4.2.bn2.running_mean, backbone.layer1.1.bn1.weight, backbone.layer2.0.downsample.1.running_mean, backbone.layer2.2.bn3.running_var, backbone.layer3.0.bn1.num_batches_tracked, backbone.layer3.3.bn3.bias, backbone.layer3.3.bn3.running_mean, backbone.layer3.0.bn1.bias, backbone.layer2.0.bn2.running_var, backbone.layer2.3.conv3.weight, backbone.layer2.3.bn1.weight, backbone.layer3.1.bn3.bias, backbone.layer4.1.bn2.num_batches_tracked, backbone.layer3.4.bn3.num_batches_tracked, backbone.layer4.2.bn3.running_var, backbone.layer1.1.bn3.running_var, backbone.layer2.0.downsample.1.num_batches_tracked, backbone.layer1.1.bn3.num_batches_tracked, backbone.layer2.0.bn2.weight, backbone.layer3.0.bn2.running_mean, backbone.layer3.2.bn3.weight, backbone.layer2.3.bn1.bias, backbone.layer3.5.bn1.bias, backbone.layer4.1.bn2.running_var, backbone.layer4.2.conv2.weight, backbone.layer3.3.bn3.running_var, backbone.layer2.2.bn2.num_batches_tracked, backbone.layer1.1.bn2.bias, backbone.layer2.0.bn1.num_batches_tracked, backbone.layer4.0.bn1.running_var, backbone.layer2.0.bn1.bias, backbone.layer3.2.bn1.bias, backbone.layer2.2.conv2.weight, backbone.layer3.2.bn2.running_mean, backbone.layer3.4.bn1.running_mean, backbone.layer3.5.conv3.weight, backbone.layer3.2.bn3.bias, backbone.layer4.0.bn3.running_var, backbone.layer3.2.bn2.bias, backbone.layer1.1.conv1.weight, backbone.layer3.1.bn1.num_batches_tracked, backbone.layer2.1.bn2.weight, backbone.layer3.3.bn2.bias, backbone.layer1.2.bn1.running_mean, backbone.layer3.4.bn3.running_var, backbone.layer1.2.bn2.running_mean, backbone.layer3.5.bn3.weight, backbone.layer1.0.downsample.1.bias, backbone.layer1.0.bn2.num_batches_tracked, backbone.layer1.1.bn3.weight, backbone.layer3.1.bn2.running_var, backbone.layer3.3.bn2.running_var, backbone.layer3.5.bn1.running_var, backbone.layer2.1.bn2.running_mean, backbone.layer3.1.conv2.weight, backbone.layer2.0.bn3.num_batches_tracked, backbone.layer2.1.conv1.weight, backbone.layer3.4.bn2.num_batches_tracked, backbone.layer2.0.conv3.weight, backbone.layer2.1.bn3.bias, backbone.layer1.0.bn1.running_mean, backbone.layer2.2.bn1.num_batches_tracked, backbone.layer3.2.bn2.weight, backbone.layer2.3.bn3.running_mean, backbone.layer3.2.bn1.running_mean, backbone.layer4.0.conv1.weight, backbone.layer2.0.bn3.weight, backbone.layer3.5.bn3.running_mean, backbone.layer4.2.bn2.bias, backbone.layer1.0.bn1.weight, backbone.layer1.1.conv3.weight, backbone.layer2.3.conv2.weight, backbone.layer3.3.conv1.weight, backbone.layer4.1.bn2.weight, backbone.layer3.0.bn1.weight, backbone.layer3.4.bn2.weight, backbone.layer1.2.conv2.weight, backbone.layer1.0.bn1.running_var, backbone.layer4.1.conv3.weight, backbone.layer3.1.bn1.running_mean, backbone.layer1.0.downsample.0.weight, backbone.layer3.1.bn2.weight, backbone.layer2.3.bn1.running_var, backbone.layer3.4.bn3.bias, backbone.layer4.2.bn3.running_mean, backbone.layer2.1.bn3.num_batches_tracked, backbone.layer4.1.bn3.weight, backbone.layer3.4.conv2.weight, backbone.layer1.0.bn2.running_mean, backbone.layer1.2.bn2.running_var, backbone.layer3.0.bn2.weight, backbone.layer2.0.bn2.num_batches_tracked, backbone.layer3.3.bn3.num_batches_tracked, backbone.layer2.1.bn3.running_var, backbone.layer3.1.bn3.running_mean, backbone.layer2.3.bn3.bias, backbone.layer3.5.bn3.bias, backbone.layer2.1.bn2.num_batches_tracked, backbone.layer4.1.bn3.num_batches_tracked, backbone.layer1.2.conv1.weight, backbone.layer1.2.bn1.running_var, backbone.layer2.3.bn1.num_batches_tracked, backbone.layer1.0.bn2.bias, backbone.layer2.3.bn3.running_var, backbone.layer3.0.bn3.num_batches_tracked, backbone.layer2.1.bn3.running_mean, backbone.layer3.3.bn2.num_batches_tracked, backbone.layer4.2.bn3.weight, backbone.layer4.0.bn3.running_mean, backbone.layer3.4.bn2.running_mean, backbone.layer2.1.bn1.running_var, backbone.layer4.0.bn1.bias, backbone.layer3.4.bn1.running_var, backbone.layer3.4.bn3.running_mean, backbone.layer1.0.conv2.weight, backbone.layer3.0.bn3.bias, backbone.layer1.0.bn3.running_mean, backbone.layer3.0.downsample.0.weight, backbone.layer3.0.downsample.1.running_var, backbone.layer3.1.bn2.bias, backbone.layer2.2.bn3.num_batches_tracked, backbone.layer3.0.bn2.bias, backbone.layer1.1.bn1.num_batches_tracked, backbone.layer3.2.bn2.num_batches_tracked, backbone.layer4.0.bn2.running_var, backbone.layer4.2.bn1.num_batches_tracked, backbone.layer1.0.bn3.bias, backbone.layer3.0.conv2.weight, backbone.layer2.3.bn2.bias, backbone.layer3.3.bn1.num_batches_tracked, backbone.layer3.3.bn2.weight, backbone.layer4.1.bn1.running_mean, backbone.layer4.2.bn1.weight, backbone.layer4.1.bn1.weight, backbone.layer3.1.bn3.weight, backbone.layer3.0.bn1.running_var, backbone.layer4.2.bn2.num_batches_tracked, backbone.layer4.2.conv3.weight, backbone.layer4.2.bn3.bias, backbone.layer3.5.bn3.num_batches_tracked, backbone.bn1.bias, backbone.bn1.running_mean, backbone.layer4.0.bn3.weight, backbone.layer4.0.bn1.num_batches_tracked, backbone.layer2.2.bn1.running_var, backbone.layer3.3.conv2.weight, backbone.layer1.0.bn1.bias, backbone.layer3.1.bn1.weight, backbone.layer3.2.bn3.running_var, backbone.layer1.1.bn3.bias, backbone.layer1.2.bn3.bias, backbone.layer2.1.bn3.weight, backbone.layer4.0.bn2.weight, backbone.layer3.2.bn2.running_var, backbone.layer4.1.bn3.running_mean, backbone.layer2.2.bn2.bias, backbone.layer2.2.bn3.bias, backbone.layer1.2.bn3.running_var, backbone.layer2.3.bn3.num_batches_tracked, backbone.layer3.0.bn3.running_mean, backbone.layer3.4.bn2.running_var, backbone.layer1.0.downsample.1.num_batches_tracked, backbone.layer1.2.bn2.bias, backbone.layer4.1.bn1.num_batches_tracked, backbone.layer1.2.bn1.weight, backbone.layer4.0.downsample.1.bias, backbone.layer1.2.bn2.weight, backbone.layer1.0.bn1.num_batches_tracked, backbone.layer1.1.bn3.running_mean, backbone.layer2.0.bn1.running_mean, backbone.layer2.3.bn2.num_batches_tracked, backbone.layer1.1.bn2.weight, backbone.layer4.0.bn1.running_mean, backbone.layer2.1.conv3.weight, backbone.layer1.0.bn3.num_batches_tracked, backbone.layer1.0.downsample.1.weight, backbone.layer3.2.conv1.weight, cls_head.fc_cls.bias, backbone.layer2.1.conv2.weight, backbone.layer1.2.bn3.num_batches_tracked, backbone.layer2.0.bn1.running_var, backbone.layer2.1.bn2.running_var, backbone.layer3.5.bn1.running_mean, backbone.layer2.0.bn2.running_mean, backbone.layer4.0.downsample.1.num_batches_tracked, backbone.layer3.0.bn2.running_var, backbone.layer4.2.bn1.running_var, backbone.layer1.1.bn1.bias, backbone.layer2.2.bn2.running_mean, backbone.layer4.2.bn1.running_mean, backbone.layer4.2.bn1.bias, backbone.layer3.1.conv1.weight, backbone.layer3.0.downsample.1.bias, backbone.layer4.0.downsample.0.weight, backbone.layer3.5.bn2.running_var, backbone.layer2.2.conv1.weight, backbone.layer2.1.bn1.bias, backbone.layer2.0.downsample.0.weight, backbone.layer4.2.bn2.weight, backbone.layer1.2.bn3.weight, backbone.layer2.0.bn1.weight, backbone.layer2.0.downsample.1.weight, backbone.conv1.weight, backbone.layer3.0.bn1.running_mean, backbone.layer3.3.bn1.running_mean, backbone.layer3.1.bn3.running_var, backbone.layer3.4.conv1.weight, backbone.layer2.2.bn3.running_mean, backbone.layer4.0.bn2.bias, backbone.layer3.0.bn3.weight

Is the pertrained weight wrong? Thanks!

OpenCV_DIR=../../third_party/opencv-4.1.0/build cmake .. should be：
OpenCV_DIR=../../opencv-4.1.0/build cmake .. . The "third_party" is not necessary.

To start with, thanks for your excellent works, it really brings a lot of convenience.
Here I would like to modify the codes to get the classification/recognition results for a single video using TSN and I3D. Since the repository is quite large, I am not sure about the exact steps to do though having some vague clues.

Specifically, can I make a dataset containing just one or a few videos and arrange it with the same structure of UCF101 so that I can also use your codes to extract frames and pre-process the video data?
Where should I add or modify the codes to present the classification results for a video (our testing video categories will be the same as those in UCF101)? I guess test_recognizer.py maybe?
And what changes do I need to make to config files?

Could you please give me some instructions to do the modifications?
By the way, Does it mean I need to install Decord and dense-flow both to realize my modifications?

Thank you so much !

I get this error in the prompt and I am not sure why, should I modify the dimensions? Or there are some data specifications missing:

completed: 0, elapsed: 0sTraceback (most recent call last):
File "tools/test_recognizer.py", line 122, in
main()
File "tools/test_recognizer.py", line 112, in main
outputs[0].shape[0]))
IndexError: list index out of range

Thanks for the help.

in mmaction/data_tools/thumos14/extracted_frames.sh we can extract both frame and optical-flow via python build_rawframes.py ../data/thumos14/videos_val/ ../data/thumos14/rawframes/ --level 1 --flow_type tvl1 --ext mp4
how can I change the command above to just extract the frame and not optical flow?
Thanks

hi @zhaoyue-zephyrus
I find training loss dropped very quickly on TSN-rgb-model when I use the pre-trainind weights to initializate. while I train the model from scratch,the training loss dropped very slow . That's amazing! So I really want to know how you pre-train the model(such as tsn-rgb-bninception,tsn-flow-bninception,i3d,...).I hope you can tell me!
thanks you!