You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for using our code! The setup of OverlapNet (pytorch) is the same as the one used in our newest work OverlapTransformer for faster retrieval, which is:
Activity
Chen-Xieyuanli commentedon Mar 17, 2022
@BIT-MJY could you please give your PyTorch setup here?
BIT-MJY commentedon Mar 18, 2022
Hello @smalltheater ,
Thanks for using our code! The setup of OverlapNet (pytorch) is the same as the one used in our newest work OverlapTransformer for faster retrieval, which is:
You can download our Torch dependences by pip:
pip3 install torch==1.10.2+cu113 torchvision==0.11.3+cu113 torchaudio==0.10.2+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.htmlor by conda:
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorchBy the way, the data used for training and evaluation here is the same as the data used in OverlapTransformer, maybe our new work can also help you.
Chen-Xieyuanli commentedon Mar 21, 2022
@BIT-MJY Thanks for the detailed reply.