-
Notifications
You must be signed in to change notification settings - Fork 219
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
transformations in MiniViT paper #224
Comments
Hi @gudrb , thanks for your attention to our work! In Mini-DeiT, the transformation for MLP is the relative position encoding
In Mini-Swin, the transformation for MLP is the depth-wise convolution layer
|
On the MiniViT paper, We make several modifi�cations on DeiT: First, we remove the [class] token. The -> Does this mean that in MiniDeiT model, IRPE is utilized (for the value), and the MLP transformation is removed, leaving only the attention transformation? |
Yes. I correct my statement. There is no transformation for FFN in Mini-DeiT. iRPE is utilized for only the key.
|
Hello, I have a question about the transformations in the MiniViT paper.
I could find the first transformation (implemented in the MiniAttention class) in the code:
Cream/MiniViT/Mini-DeiT/mini_vision_transformer.py
Line 104 in 4a13c40
However, i couldn't find the second transformation in the code (which should be before or inside the MLP in the MiniBlock class)
Cream/MiniViT/Mini-DeiT/mini_vision_transformer.py
Line 137 in 4a13c40
Could you please let me know where the second transformation is?
The text was updated successfully, but these errors were encountered: