Closed EvgeniaChroni closed 2 years ago
Hi there, thanks for reaching out. Can you elaborate more details of your training settings (e.g. learning rate, pretrained model, epochs, and batchsize)? What's the accuracy you got?
Yeah sure , I use Sign_Isolated_Conv3D_clip.py to run the code. num_classes = 2000 epochs = 100 batch_size = 32 learning_rate = 1e-3
I also use the pretrained model that you provide but I train only the last layer (model.fc1 = nn.Linear(model.fc1.in_features, num_classes)).
The accuracy is about 10%
Thank you again
I see. So I think you can try to train the whole network instead. (load the pretrained model, pop the last fc layer, and append a new fc layer with 2000 classes) For your reference, I trained the whole network and got 47.51% top-1 per-instance accuracy for RGB frames.
Ok thank you for the info.
I also used gen_frames.py for data preprocessing and same sample_duration=32
Are you planning to provide code also for WLASL?
I did the same thing for data preprocessing as well. Yes, we are preparing a journal extension of this workshop paper. A preprint version with code will be released shortly (targeting this month).
I did the same thing for data preprocessing as well. Yes, we are preparing a journal extension of this workshop paper. A preprint version with code will be released shortly (targeting this month). Already looked at your preprint version, and I've learned a lot from your current code. I am looking forward to your released code! Thank you for your share!
Hello thank you so much for your code.
I am trying to train Conv3D for WLASL dataset but the accuracy is too low. Do you have any idea why this is happening ?
Thank you in advance.