Skip to content

Latest commit

 

History

History
43 lines (38 loc) · 1.93 KB

README.md

File metadata and controls

43 lines (38 loc) · 1.93 KB
Raw

Instance Segmentation

Models

  • Path Aggregation Network (PANet)
  • Segmenting Objects by Locations (SOLOv2)
  • Hierarchical Vision Transformer using Shifted Windows (SWIN-T)

Results

PANet
SOLOv2
SWIN-T




Installation

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