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.

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

Support det+cls+rec online prediction pipeline, improve RecResizeNormForInfer to fix bug in single img predict_rec #435

Draft
wants to merge 8 commits into
base: main
Choose a base branch
from

Conversation

HaoyangLee
Copy link
Collaborator

Thank you for your contribution to the MindOCR repo.
Before submitting this PR, please make sure:

Motivation

  • Add predict_cls and det+cls(optional)+rec online prediction pipeline.
  • When run single image prediction in predict_rec.py, padding=False, keep_ratio=True, target_width=None, which will raise bug in RecResizeNormForInfer. Now fix it to support target_width=None.

Related Issues and PRs

Issue #238

add text direction classification model (mobilenetv3_small_100)

add text direction classification model (mobilenetv3_small_100)

add text direction classification model (mobilenetv3_small_100)

add text direction classification model (mobilenetv3_small_100)

add text direction classification model (mobilenetv3_small_100)

add cls_mv3

update typo in clspostprocess

update cls data converter

cls run on grpah mode

fix rebase change

update cls data converters

update config files

tidy up code

tidy up code

update cls model class name

update cls postprocess and metric

rm cls data converter, update in another PR

fix CI failure

tidy up code

fix bug

update yaml
add predict_cls

add predict_cls

update online predict

update  online prediction

fix predict_cls bug, chw->hwc

format code

format code2
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please refer to the arg naming in ppocr for low-cost transfer.

https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/tools/infer/utility.py#L114C1-L120C65

@HaoyangLee HaoyangLee marked this pull request as draft July 6, 2023 12:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants