mmocr/projects
Tong Gao 5670695338
[SPTS] train (#1756)
* [Feature] Add RepeatAugSampler

* initial commit

* spts inference done

* merge repeat_aug (bug in multi-node?)

* fix inference

* train done

* rm readme

* Revert "merge repeat_aug (bug in multi-node?)"

This reverts commit 393506a97c.

* Revert "[Feature] Add RepeatAugSampler"

This reverts commit 2089b02b48.

* remove utils

* readme & conversion script

* update readme

* fix

* optimize

* rename cfg & del compose

* fix

* fix

* tmp commit

* update training setting

* update cfg

* update readme

* e2e metric

* update cfg

* fix

* update readme

* fix

* update
2023-03-07 14:18:01 +08:00
..
ABCNet [Fix] change cudnn benchmark to false (#1705) 2023-02-03 18:57:12 +08:00
SPTS [SPTS] train (#1756) 2023-03-07 14:18:01 +08:00
example_project [Projects] Refine example projects and readme (#1628) 2022-12-27 09:29:22 +08:00
README.md [Projects] Refine example projects and readme (#1628) 2022-12-27 09:29:22 +08:00

README.md

Projects

Implementing new models and features into OpenMMLab's algorithm libraries could be troublesome due to the rigorous requirements on code quality, which could hinder the fast iteration of SOTA models and might discourage our members from sharing their latest outcome here.

And that's why we have this Projects/ folder now, where some experimental features, frameworks and models are placed, only needed to satisfy the minimum requirement on the code quality, and can be used as standalone libraries. Users are welcome to use them if they use MMOCR from source.

Everyone is welcome to post their implementation of any great ideas in this folder! If you wish to start your own project, please go through the example project for the best practice.

Note: The core maintainers of MMOCR only ensure the results are reproducible and the code quality meets its claim at the time each project was submitted, but they may not be responsible for future maintenance. The original authors take responsibility for maintaining their own projects.