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
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?
Branch
main branch (1.x version, such as
v1.0.0
, ordev-1.x
branch)Prerequisite
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:
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
test.txt is following
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