- Path Aggregation Network (PANet)
- Segmenting Objects by Locations (SOLOv2)
- Hierarchical Vision Transformer using Shifted Windows (SWIN-T)
| PANet |  |
|---|---|
| SOLOv2 |  |
| SWIN-T |  |
select the model to
docker build -t <image-name> <Dockerfile path>
docker run --gpus all --name <container-name> -dit --ipc host \
-v <path-on-your-pc>:/shared_area <image-name>
docker exec -it <container-name> bash
cp /shared_area/infer_model.bash /workspace/<model-name>
cp /shared_area/video_demo.py <model-repo>/tools
ln -s /shared_area/<pretrained-weights> <model-repo>/checkpoints| model | config | checkpoint |
|---|---|---|
| PANet | e2e_panet_R-50-FPN_2x_mask | panet_mask_step179999 |
| SOLOv2 | solov2_x101_dcn_fpn_8gpu_3x | SOLOv2_X101_DCN_3x |
| SWIN-T | mask_rcnn_swin_tiny_patch4_3x_coco | mask_rcnn_swin_tiny_patch4_window7 |