Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
I tried running extract_c3d_features.sh and I get the following error:
E0212 18:47:51.618083 9049 io.cpp:169] Could not open or find file /media/TB/UCF-101/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c01
F0212 18:47:51.618093 9049 video_data_layer.cpp:77] Check failed: read_video_result Could not load /media/TB/UCF-101/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c01 at frame 1.
How do I go about fixing this? Also, how do I extract c3d features for my videos?
I tried running extract_c3d_features.sh and I get the following error:
E0212 18:47:51.618083 9049 io.cpp:169] Could not open or find file /media/TB/UCF-101/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c01
F0212 18:47:51.618093 9049 video_data_layer.cpp:77] Check failed: read_video_result Could not load /media/TB/UCF-101/ApplyEyeMakeup/v_ApplyEyeMakeup_g01_c01 at frame 1.
How do I go about fixing this? Also, how do I extract c3d features for my videos?