953585130

Hi! Thank you for your contribution to computer vision. My question is whether I can extract the video descriptors I need from this network. I need the feature representation of...

I want to extract the characteristics of my video through tensorflow

2

Hi， Thank you for your code! I built the environment and trained the C3D model from scratch, and the test also achieved good precision. Next I want to use this...

I tried to modify the code to fine-tune (my own dataset), but it always failed. How should I modify it? saver = tf.train.Saver(weights.values() + biases.values()) init = tf.global_variables_initializer() # Create...

extract_features.bin : not found

2

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...

About the setting of mini_batch_size and number_of_mini_batches

1

Hi, I have successfully compiled C3D-v1.0, and the features of the two small screens inside have been successfully extracted. Then I randomly selected 6 videos in ucf101, then extracted them...

I put 20 videos selected from ucf101 continuously in the input file. After running the code, I can only extract the first two. From the third output folder, it is...

Hello, I have placed 20 of my own video files in succession. Only the features of the first 3 video screens are correctly extracted in the output file. The fourth...

I would like to ask the caffe version must use the modified version you provided? Can a normal version of caffe support C3D? Help!!!