Beanocean

@Zealoe When conducting convolution operation with stride 2, the size of feature map will be divided by 2. In order to match the sizes of feature map in corresponding convolution...

@joehoeller @getcontrol The path of val dataset is required, change the command as follow: python train.py \ --train_dataset images_folder/ \ **_--val_dataset images_folder_2/ \. # Added Line_** --device 'cuda:0' --epochs 10...

> Did you export this code to pytorch? @mememimis, I have exported it to Pytorch. But still, have some troubles. I will release the code later, hope you can help...

If I want to train the model on my own data, how should I prepare the C3D features of video. I didn't find corresponding files in your project. @yaoli