search

scene-verse / SceneVerse

Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"
https://scene-verse.github.io
MIT License
194 stars 3 forks source link

Issue in Evaluation #26

Open Yangl1nFeng opened 1 month ago

Yangl1nFeng commented 1 month ago

FileNotFoundError: Cannot find pytorch_model.bin in /SceneVerse-main/results/FinalOVPretrain_b64_Pretrain_scanrefer_no_note/2024-10-10-09:23:20.509828/ckpt/best.pth.

Hello! I don't understand why I have trained correctly but got the .safetensors model instead of the .bin model. I don't know if there is something wrong?

Buzz-Beater commented 2 weeks ago

Hi, can you try checking if the transformers package's version matches the provided one in the requirements.txt? It could be updated by the Huggingface Transformers repo. Meanwhile, you can also try checking out the provided checkpoints in TRAIN.md to see if the pipeline walks through :-)