Conv3D for WLASL

[jackyjsy]

Conv3D for WLASL

[jackyjsy]

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?

[EvgeniaChroni]

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

[jackyjsy]

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.

[EvgeniaChroni]

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?

[jackyjsy]

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).

[LiangSiyv]

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!