Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[models] Implement HRGAN or MASTER #215

Closed
charlesmindee opened this issue Apr 26, 2021 · 1 comment · Fixed by #300
Closed

[models] Implement HRGAN or MASTER #215

charlesmindee opened this issue Apr 26, 2021 · 1 comment · Fixed by #300
Assignees
@charlesmindee
Labels
module: models Related to doctr.models type: enhancement Improvement
Milestone
1.0.0

Comments

@charlesmindee
Copy link
Collaborator

This paper suggests a new architecture: Holistic Representation Guided Attention Network for text recognition model, inspired from transformers, which oustands SAR both in accuracy & speed.

We should implement this model, but the impressive speed results should be handled carefully (X8 speed compared to SAR), since the experiments are conducted on a GPU, and this model is highly parallelable (no recurrency). Is this new model so fast on CPU ?
@charlesmindee charlesmindee added type: enhancement Improvement module: models Related to doctr.models labels Apr 26, 2021
@charlesmindee charlesmindee added this to the 1.0.0 milestone Apr 26, 2021
@charlesmindee charlesmindee self-assigned this Apr 26, 2021
@charlesmindee charlesmindee changed the title [models] Implement HRGAN [models] Implement HRGAN or MASTER Jun 4, 2021
@charlesmindee
Copy link
Collaborator Author

This one seems to be even stronger

@charlesmindee charlesmindee mentioned this issue Jun 9, 2021
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@charlesmindee charlesmindee

Labels
module: models Related to doctr.models type: enhancement Improvement
Projects
None yet
Milestone
1.0.0
Development

Successfully merging a pull request may close this issue.

feat: add MASTER in models.recognition module mindee/doctr
1 participant
@charlesmindee