search

yangcaoai / CoDA_NeurIPS2023

Official code for NeurIPS2023 paper: CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection
https://yangcaoai.github.io/publications/CoDA.html
MIT License
175 stars 15 forks source link

Dataset could not access #12

Closed EinOnly closed 1 month ago

EinOnly commented 2 months ago

https://hkustconnect-my.sharepoint.com/:f:/g/personal/ycaobd_connect_ust_hk/EqeHrtMq5aZBmnZUR79vub4B9HZIBxYLd5K7z6VuvemHzg?e=e7ooDv can not open now.

yangcaoai commented 2 months ago

Hi, it's fixed. Please have a check.

EinOnly commented 2 months ago

Thanks! Btw, Does the program generate images like the image in the paper? I just made some hack to run it without your dataset, just get a *.lst file.

yangcaoai commented 2 months ago

It seems that you are evaluating the models by 'bash test_release_models.sh', so you will get the performance numbers in the *.lst files. If you want to predict samples, you can do so by running 'bash run_samples.sh'.