What's Changed

Highlights

• Support BEiT: BERT Pre-Training of Image Transformers
• Support K-Net: Towards Unified Image Segmentation
• Add avg_non_ignore of CELoss to support average loss over non-ignored elements
• Support dataset initialization with file client

New Features

• Support BEiT: BERT Pre-Training of Image Transformers (#1404)
• Support K-Net: Towards Unified Image Segmentation (#1289)
• Support dataset initialization with file client (#1402)
• Add class name function for STARE datasets (#1376)
• Support different seeds on different ranks when distributed training (#1362)
• Add nlc2nchw2nlc and nchw2nlc2nchw to simplify tensor with different dimension operation (#1249)

Improvements

• Synchronize random seed for distributed sampler (#1411)
• Add script and documentation for multi-machine distributed training (#1383)

Bug Fixes

• Add avg_non_ignore of CELoss to support average loss over non-ignored elements (#1409)
• Fix some wrong URLs of models or logs in ./configs (#1336)
• Add title and color theme arguments to plot function in tools/confusion_matrix.py (#1401)
• Fix outdated link in Colab demo (#1392)
• Fix typos (#1424, #1405, #1371, #1366, #1363)

Documentation

• Add FAQ document (#1420)
• Fix the config name style description in official docs(#1414)

New Contributors

• @kinglintianxia made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1371
• @CCODING04 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1376
• @mob5566 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1401
• @xiongnemo made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1392
• @Xiangxu-0103 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1405