Pikaliov
1b3206b6a7
- Add enhanced README with project structure and quick start guide - Initialize repository with DCNv4 CUDA extension (PyTorch module) - Include classification, detection, and segmentation subdirectories - Reference upstream OpenGVLab DCNv4 implementation Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
3.7 KiB
3.7 KiB
ADE20K
Introduced by Zhou et al. in Scene Parsing Through ADE20K Dataset.
The ADE20K semantic segmentation dataset contains more than 20K scene-centric images exhaustively annotated with pixel-level objects and object parts labels. There are totally 150 semantic categories, which include stuffs like sky, road, grass, and discrete objects like person, car, bed.
Model Zoo
UperNet + InternImage
| backbone | resolution | mIoU (ss/ms) | Config | Download |
|---|---|---|---|---|
| FlashInternImage-T | 512x512 | 49.3 / 50.3 | config | ckpt | log |
| FlashInternImage-S | 512x512 | 50.6 / 51.6 | config | ckpt | log |
| FlashInternImage-B | 512x512 | 52.0 / 52.6 | config | ckpt | log |
| FlashInternImage-L | 640x640 | 55.6 / 56.0 | config | ckpt | log |
- Training speed is measured with A100 GPU.
- Please set
with_cp=Trueto save memory if you meetout-of-memoryissues. - The logs are our recent newly trained ones. There are slight differences between the results in logs and our paper.
Mask2Former + InternImage
| backbone | resolution | mIoU (ss) | Config | Download |
|---|---|---|---|---|
| FlashInternImage-T | 512x512 | 51.2 | config | ckpt | log |
| FlashInternImage-S | 640x640 | 52.2 | config | ckpt | log |
| FlashInternImage-B | 640x640 | 53.4 | config | ckpt | log |
| FlashInternImage-L | 640x640 | 56.7 | config | ckpt | log |