-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
GradCAM for SwinTransformer #84
Comments
What was class_index used in the example above? |
I fine-tuned the model with a classifier head on a specific a dataset. It's not a part of ImageNet. |
OK There are several different issues here. The swin transformer, deviates from vit:
|
Yes, the ViT dosen't have the CLS token. |
Cool!
|
Closing this issue, since it seems resolved. |
Hi @AmbiTyga, @jacobgil ! Thank you in advance for your help. |
@scott870430 Hi, I had a similar problem with you, have you figured out why? |
@SKBL5694 Unfortunately, I couldn't figure out how to solve it, and ultimately, I gave up. |
@scott870430 Ok, I'll explore and let you know if I have any results, thanks for the reply |
I am using image models from timm package.
Similar to ViT, I tried accessing normalization layer of last block of last layer in SwinTransformer. After using GradCAM++ the results from ViT and swin transformer have a huge difference, Swin transformer's accuracy is better than ViT but the gradient map is very different. I would like to know am I using right layer of Swin Transformer or should change some configurations in the GradCamPlusPlus module.
Original Image
ViT GradCam++
Swin Transformer GradCAM++
The text was updated successfully, but these errors were encountered: