Hello author, may I ask why there is no stage1.sh file in the tools file

[1404710698]

No description provided.

[MinghanLi]

Thanks for your attantion.

Stage1 is trained on two machines, each equipped with eight V100 or A100 GPUs, and the code supports PyTorch's native multi-node and multi-GPU parallelism. If you want to train Stage1, you simply need to modify the configuration file for Stage2 located in the tools directory. Here are the steps:

Step 1: Configure the parameters for multi-node and multi-GPU parallelism. For detailed instructions, refer to Detectron2's launch script documentation.

Step 2: Change the configuration file from --config-file configs/univs/univs_r50_stage2.yaml to --config-file configs/univs/univs_r50_stage1.yaml.

[MinghanLi]

Dear Zhao, You can find more detailed instructionz from https://github.com/MinghanLi/UniVS/blob/main/datasets/README.md . Thanks. Best, Minghan zhao ***@***.***> 于2024年5月16日周四 17:07写道：

…

Again, I would like to inform cfg. MODEL. UniVS.CLIP_CLASS_EMBED_PATH = 'datasets/concept_emb/combined_datasets_cls_emb_rn50x4.pth' where should I download the weight file here, thank you very much! — Reply to this email directly, view it on GitHub <#7 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHOANLQGMTTA4WBXTTXT5RLZCRZNZAVCNFSM6AAAAABHVI2UUWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMJUGYYTQOBUG4> . You are receiving this because you commented.Message ID: ***@***.***>

[1404710698]

Thanks to the author for the reply and I wish you all the best in your work!