Min Wang

> It's a typo and I tried fixing it and re-trained one of the models on LineMOD, finding that the performance is close. Considering the cost of re-training all pre-trained...

Thank you for your reply! > The framework of CNN and PCN is kept the same as their original version. Note that the main idea is to do full flow...

Hi Yisheng, There is no KNN feature gathering in fusion module from point to rgb.  

Hi Yisheng, Thank you for your reply ! > The framework of CNN and PCN is kept the same as their original version. Note that the main idea is to...

Thank you for your patience! > * The upsampling module also serves as the KNN correspondence feature gathering function here. It is like gathering neighbors feature to make the size...

> We are facing the same errors/warnings. It tells you that your version of TensorFlow is not compatible with the CUDA / cuDNN version installed by PyTorch. However, we do...

> The tf errors disappear after loading cuda 10.0.130 and cudnn 10.1_v7.5 The mIoU decreases in this case so I changed them back to 10.1 and 7.6 respectively.

Thanks for your information. I thought you used grid search and set the best hyperparameters as default values, right? That's why I feel confused.

Hi Daniel Thank you for your reply. Both of us used the same network configuration (network depth, block type, fusion, upsampling, ...) since we run default configuration. I just followed...

> I try to run multiple times now and see if there is a performance boost. I just checked the results of another runs - epoch 257. It seems that...