Shuting He

Thank you for your interest in our work! Backbone weights is used in the training process. step1: python tools/process_ckpt.py step2: python train_net_lmpm.py \ --config-file configs/lmpm_SWIN_bs8.yaml \ --num-gpus 8 --dist-url auto...

Thank you for your interest in our work! The checkpoint had been released here: https://drive.google.com/file/d/1YLnRUsANuPVfLo1jrgK05EGUJglrwA9H/view

You can refer to [ReferFormer](https://github.com/wjn922/ReferFormer) for this information. Thank you for your interest!

Go to the README and find and follow the section "Training". using the command: `CUDA_VISIBLE_DEVICES=0 python train_net.py --config-file configs/{}-segmentation/PADing.yaml --num-gpus 1 MODEL.WEIGHTS pretrained_weight_{}.pth` {} can be semantic,instance and panoptic. I...

You can refer to https://github.com/facebookresearch/detectron2/blob/main/tools/visualize_json_results.py to visualize json results.

Thank you for your interest! GPU is necessary for the code. Thanks!

Thank you for your interest in our work! https://drive.google.com/drive/folders/1QCD-0MXtGOJQdexjelOlOlx7MvUphaEZ You can refer to README.md to see more released models.

Thank you for your interest in our work! You can refer to this issue to reproduce the result. #7

Thank you for your interest! You can refer to https://github.com/zhengye1995/Zero-shot-Instance-Segmentation/issues/42 Hope this is helpful for you!