-
Notifications
You must be signed in to change notification settings - Fork 34
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
train error: AttributeError: 'tuple' object has no attribute 'log_softmax' #6
Comments
Hi, Lines 484 to 488 in 9f71792
and here Lines 678 to 690 in 9f71792
If you train without token labeling, We suggest you add |
@zihangJiang Thanks for your response. I train without token labeling, because I have not generate token labels for my custome dataset.
Is this mean if I want to train without token labeling, I can't use pretrain model ? |
We haven't tested on other datasets yet, but you can of course use the pre-trained model. I think you can add However, some other bugs may occur. You can wait for our further update supporting transfer learning. |
Well, thanks, expect for further update. |
Hi @lxy5513 , We've updated and tested support for transfer learning. The dataset folder structure should be the same as ImageNet structure https://github.com/zihangJiang/TokenLabeling#requirements (with Let me know if you have any further questions. |
Hi, thanks for you great work. When I train script, some error occurs:
AttributeError: 'tuple' object has no attribute 'log_softmax'
and loss function is
train_loss_fn = LabelSmoothingCrossEntropy(smoothing=0.0).cuda()
by the way: Could you please tell me why we need to specify smoothing=0.0?
The text was updated successfully, but these errors were encountered: