谢昕辰 53fe1ccf39 [Feature] Support MMSegInferencer (#2413) ... ## Motivation Support `MMSegInferencer` for providing an easy and clean interface for single or multiple images inferencing. Ref: https://github.com/open-mmlab/mmengine/pull/773 https://github.com/open-mmlab/mmocr/pull/1608 ## Modification - mmseg/apis/mmseg_inferencer.py - mmseg/visualization/local_visualizer.py - demo/image_demo_with_inferencer.py ## Use cases (Optional) Based on https://github.com/open-mmlab/mmengine/tree/inference Add a new image inference demo with `MMSegInferencer` - demo/image_demo_with_inferencer.py ```shell python demo/image_demo_with_inferencer.py demo/demo.png fcn_r50-d8_4xb2-40k_cityscapes-512x1024 ``` --------- Co-authored-by: MeowZheng <meowzheng@outlook.com>		2023-02-23 21:16:19 +08:00
..
__init__.py	CodeCamp #141 [Feature] Add BioMedical3DRandomFlip. (#2404)	2023-01-20 15:34:11 +08:00
formatting.py	[Enhancement]Replace numpy ascontiguousarray with torch contiguous to speed-up (#2604)	2023-02-15 19:02:00 +08:00
loading.py	[Feature] Support MMSegInferencer (#2413)	2023-02-23 21:16:19 +08:00
transforms.py	CodeCamp #141 [Feature] Add BioMedical3DRandomFlip. (#2404)	2023-01-20 15:34:11 +08:00