C3D icon indicating copy to clipboard operation
C3D copied to clipboard

C3D is a modified version of BVLC caffe to support 3D ConvNets.

Results 76 C3D issues
Sort by recently updated
recently updated
newest added

Try to extract features with default values on CPU and got this error: Do you have any idea about this error @dutran @puneet29 ```[Info] trained_model=/app/examples/c3d_feature_extraction/conv3d_deepnetA_sport1m_iter_1900000 found. Good to go! os.getcwd()...

I have caffe version 1.0.0 installed and it compiled correctly with video_data_layer included. When I run c3d_resnet18_sports1m_r2_iter_2800000.caffemodel for feature extraction I get the error for Video Data layer, which is...

I1130 15:35:32.397227 25336 net.cpp:322] Copying source layer relu5a I1130 15:35:32.397253 25336 net.cpp:322] Copying source layer conv5b I1130 15:35:32.474161 25336 net.cpp:322] Copying source layer relu5b I1130 15:35:32.474186 25336 net.cpp:322] Copying source...

I'm running the project in a docker container, but I can not execute the command `sh c3d_sport1m_feature_extraction_frm.sh` from the C3D Feature Extraction session of the C3D User Guide. I have...

I have build the c3d-v1.0 model successfully and tried to extract the features for my .mp4 video for every 16 frames. I have generated the 'input_list_video.txt' and 'output_list_video_prefix.txt'. The features...

Hi, This is for those who want to use C3D in Google Colab. **It works like a charm.** LINK: https://github.com/dolongbien/HumanBehaviorBKU/blob/master/C3D/C3DV0.ipynb

Hello, when I execute sh c3d_sport1m_feature_extraction_frm.sh file,The reported error is ../../build/tools/extract_image_features.bin : not found. However, the extract_features.bin file exists in my caffe. I have not found a lot of documents...

I am trying to train UCF-101 dataset on the C3D-v1.1 but i face a weird error. The frame which is being accessed is one number more than the last frame...

I am currently working on a computer vision problem statement for which I use C3D on CPU only mode. It works great, but feature extraction on my dataset of videos...