MMOCR Release v1.0.0rc3

Highlights

1. We release several pretrained models using oCLIP-ResNet as the backbone, which is a ResNet variant trained with oCLIP and can significantly boost the performance of text detection models.

2. Preparing datasets is troublesome and tedious, especially in OCR domain where multiple datasets are usually required. In order to free our users from laborious work, we designed a Dataset Preparer to help you get a bunch of datasets ready for use, with only one line of command! Dataset Preparer is also crafted to consist of a series of reusable modules, each responsible for handling one of the standardized phases throughout the preparation process, shortening the development cycle on supporting new datasets.

New Features & Enhancements

• Add Dataset Preparer by @xinke-wang in #1484
• support modified resnet structure used in oCLIP by @HannibalAPE in #1458
• Add oCLIP configs by @gaotongxiao in #1509

Docs

• Update install.md by @rogachevai in #1494
• Refine some docs by @gaotongxiao in #1455
• Update some dataset preparer related docs by @xinke-wang in #1502
• oclip readme by @Harold-lkk in #1505

Bug Fixes

• Fix offline_eval error caused by new data flow by @gaotongxiao in #1500

New Contributors

• @rogachevai made their first contribution in #1494
• @HannibalAPE made their first contribution in #1458

Full Changelog: v1.0.0rc2...v1.0.0rc3