[Bug] How can I use clip_feature_extraction.py to input the rawframes , and then output the RGB features of each frame?

Question

[Bug] How can I use clip_feature_extraction.py to input the rawframes , and then output the RGB features of each frame?

Chenhongchang opened this issue 4 months ago · comments

CHC commented 4 months ago

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

I have searched Issues and Discussions but cannot get the expected help.
I have read the documentation but cannot get the expected help.
The bug has not been fixed in the latest version.

Environment

sys.platform: linux
Python: 3.7.7 (default, May 7 2020, 21:25:33) [GCC 7.3.0]
CUDA available: True
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 3090
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.4, V11.4.152
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.7.1+cu110
PyTorch compiling details: PyTorch built with:

GCC 7.3
C++ Version: 201402
Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.0
NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80
CuDNN 8.0.5
Magma 2.5.2
Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.8.2+cu110
OpenCV: 4.8.1
MMEngine: 0.10.1
MMAction2: 1.2.0+4d6c934
MMCV: 2.1.0
MMDetection: 3.2.0
MMPose: 1.2.0

Describe the bug

I followed the documentation and went with Option 2 to build my custom dataset. To study how to extract the feature, my dateset include 135 RGB frames which extract from a video in THUMOS14. When I reached step 6, I used tools\misc\clip_feature_extraction.py to extract features from my rawframes dataset. However, I encountered an issue: it produce a .pkl file of 2048 (feature dimension) x 1 (number of features) rather than 2048 (feature dimension) x 135 (number of features equals to number of frames ). How can I use clip_feature_extraction.py to input the rawframes , and then output the RGB features of each frame?

Reproduces the problem - code sample

No response

Reproduces the problem - command or script

the following code is the conmmad which I executed

python /home/bit/mmaction2/tools/misc/clip_feature_extraction.py 
/home/bit/mmaction2/configs/recognition/tsn/testa.py 
/home/bit/mmaction2/tsn_r50_320p_1x1x8_50e_activitynet_clip_rgb_20210301-c0f04a7e.pth 
/home/bit/mmaction2/data/rgb_feat 
--video-list /home/bit/mmaction2/data/test/test.txt
--video-root /home/bit/mmaction2/data/test/rawframes

test.txt is following

/home/bit/mmaction2/data/test/rawframes/video_test_0000004 135

Reproduces the problem - error message

it produce a .pkl file of 2048 (feature dimension) x 1 (number of features) rather than 2048 (feature dimension) x 135 (number of features equals to number of frames ). How can I use clip_feature_extraction.py to input the rawframes , and then output the RGB features of each frame?

Additional information

No response