-
Notifications
You must be signed in to change notification settings - Fork 320
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
Merge current dev to main #154
Conversation
…PaddleViT into focal_transformer
this function at FocalTransformerBlock-Class, Line at [638, 668, 677].
Add Relative position embedding in model. It was mentioned in the official parameter before, but it was not enabled, now it is added
Fix the situation of Focal Level greater than 2, test Level 3 is ok!
fix bug in datasets:
fix bug in all readme.md
… scale hvt models
Add hvt_s1_patch16_224 config file and modify config detail.
add multi scale sampler, update model and result
add training for classification models
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.
LGTM,不过 crossvit 的图片需要小改一下,大致没问题哈
readme |
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.
LGTM
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.
np
Most classification models now is able to train using single and multiple GPUs (Except BeiT and VOLO which needs other algorithms during training). So I open this PR and prepare a new version release for main branch.