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
The diagnoal matrix meaning? #16
Comments
Sorry for the late reply.
|
Thanks for your reply! |
Thank you for your reply. You said lamq is the diagonal element of matrix A. But the "pos_transformation" obtained after FFN does not extract diagonal elements, but directly performs point multiplication with "query_sine_embedded", that is, "query_sine_embedded=query_sine_embedded * pos_transformation". Can you explain the principle? |
@WYHZQ Have you figured it out? I have the same confusion. |
Hi, thank your nice work about Transformer in Object Detection. But I have some questions when reading the paper and code. I hope you can give me some answers。
What 's the insight of the pos_transformation T in 3.3 ?
What 's the meaning about diagonal vector \lamda q described in 3.3. And I don't find the code about the diagonal operator in this repo. And i just find the pos_transformation just generated by learnable weights :
ConditionalDETR/models/transformer.py
Line 151 in 0b04a85
I can't figure out the difference bewteen "Block" , "Full" and "Diagonal" in Fig5.
The above are all my questions. I sincerely hope I can get your help. Thanks!
The text was updated successfully, but these errors were encountered: