Kunjal1999

> You have the issue, possibly because of #49. Please try to build the .whl file on your own. Our team is very busy recently due to several paper deadlines,...

> Hi @Kunjal1999, thanks for the comments. > > You couldn't import the library because you haven't built the library successfully. So you should check the library building process. Here...

> After training, in this [line](https://github.com/muhanzhang/pytorch_DGCNN/blob/50f504131ca66382f3f078ae98e59aa3ae35b795/main.py#L234), you can add a `torch.save(classifier.state_dict(), your_model_save_path)` to save the trained model. Then, next time, you can skip the training and load the saved model...

> You can use loop_dataset(): > > https://github.com/muhanzhang/pytorch_DGCNN/blob/50f504131ca66382f3f078ae98e59aa3ae35b795/main.py#L223 Loss, accuracy and logits are generated inside the loop_dataset() function. Where are the predicted values?

> https://github.com/muhanzhang/pytorch_DGCNN/blob/50f504131ca66382f3f078ae98e59aa3ae35b795/main.py#L151 > > `pred` are the predictions. Thanks, those are when classifier.regression is True (line 150). What if classifier.regression is False? (line 153)

Could you kindly provide more specific details regarding the modifications needed to get higher resolution images?

Hello, I don't want a complete blank output, I want it to be controlled upto 1000 lines.