Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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
[models] add ViTSTR TF and PT and update ViT to work as backbone #1055
[models] add ViTSTR TF and PT and update ViT to work as backbone #1055
Changes from all commits
d93f906
0112abd
1109bd4
9eefdfd
11e16e0
fa86a46
657dbca
c59f1c3
13f4fe4
f7a6bb4
8c39d29
2c726dd
ef6ae17
3757269
8931c19
fd72484
854f0ef
cf8470e
b84892f
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
tricky condition: what are all the possible cases as input, and what do we want as patch_size for each?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
oh it could be anything ..
currently in classification case: 32x32 -> (4, 4 (check)
recognition case: 32x128 -> (4, 8) (check)
detection case 1024x1024 (not handled)
any other size (not handled)
it will not fail but each size needs a different patch_size
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ok two questions then:
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(4, 16) would work also but i used the values from ParSeq for the PatchEmbedding of 32x128 samples
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
which is (4, 8)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
https://github.com/baudm/parseq/blob/main/configs/model/parseq.yaml
https://github.com/baudm/parseq/blob/main/configs/experiment/vitstr.yaml
If we would use a fixed ratio this would be easy to scale ... but yeah i took the values from ParSeq paper / implementation