search

3d-vista / 3D-VisTA

Official implementation of ICCV 2023 paper "3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment"
https://3d-vista.github.io
MIT License
189 stars 11 forks source link

Can not find scanrefer_corpus.pth & scanrefer_vocab.pth? #6

Closed Xiaolong-RRL closed 1 year ago

Xiaolong-RRL commented 1 year ago

Dear author:

Thanks for your interesting work.

According to the instructions in the readme, I didn't find these two files: scanrefer_corpus.pth & scanrefer_vocab.pth, could you tell me how to find them correctly?

Thanks!!

Xiaolong-RRL commented 1 year ago

Another question:

I noticed that the checkpoints' names seem to be wrong, are they correct?

zhuziyu-edward commented 1 year ago

Hi, we have updated checkpoints path in readme you can check again.

zhuziyu-edward commented 1 year ago

You can build scanrefer_corpus.pth from dataest/scan2cap.py and scanrefer_vocab.pth from utils/build_vocabulary.py

Xiaolong-RRL commented 1 year ago

I see, thanks!!