v1.0.0rc6(03/03/2023)

Highlights

• Support MMSegInferencer (#2413, #2658), which is a easy-to-use hight level api for model inference.

>>> from mmseg.apis import MMSegInferencer
>>> # Initialize an inference
>>> inferencer = MMSegInferencer(model='deeplabv3plus_r18-d8_4xb2-80k_cityscapes-512x1024')
>>> # Inference
>>> inferencer('demo/demo.png', show=True)
>>> # Get all models in MMSegmentation
>>> models = MMSegInferencer.list_models('mmseg')

• Support REFUGE dataset (#2554)

Features

• Add browse_dataset.py script in mmsegmentation/tools/ (#2649)
• Support auto import modules from registry (#2481)
• Replace numpy ascontiguousarray with torch contiguous to speed-up (#2604)

Bug fix

• Rename and Fix bug of projects HieraSeg (#2565)
• Add out_channels in CascadeEncoderDecoder and update OCRNet and MobileNet v2 results (#2656)

Documentation

• Add dataflow documentation of Chinese version (#2652)
• Add customized runtime documentation of English version (#2533)
• Add documentation for visualizing feature map using wandb backend (#2557)
• Add documentation for benchmark results on NPU (HUAWEI Ascend) (#2569, #2596, #2610)
• Fix API name error in the migration doc (#2601)
• Refine projects documentation (#2586)
• Refine MMSegmentation documentation (#2668, #2659)

New Contributors

• @zccjjj made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/2548
• @liuruiqiang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/2554
• @wangjiangben-hw made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/2569
• @jinxianwei made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/2557