Mu Hu

> @JUGGHM Thanks for your excellent work. I am trying to re-implement your training process, but there's a few questions confused me: > > 1. Whether the larger batch size...

Thanks for your interest! It's the same model as it is benchmarked on _**test**_ set while validated on **_val_** set. You could also refer to [this issue](https://github.com/JUGGHM/PENet_ICRA2021/issues/23).

> how to use penet pre-trained model,why it name is end with .tar it seems cant be loaded by "checkpoint = torch.load(args.evaluate, map_location=device)" Thanks for your interest! I am afraid...

Thanks for your interest! You could refer to [this question](https://github.com/JUGGHM/PENet_ICRA2021/issues/11).

> Hi, recently, I had trained net as you teach me, but I met other questions, I want to run the test model, I don't know the data type of...

Thanks for your interest! Actually the accelerated CSPN is originally designed for dilated CSPN as the sample and stitch steps are time consuming. And the introduced unfolding operation is time...

Thanks for your interest! In this work, the confidence maps are neat because we impose intermediate supervision on their corresponding depth maps respectively, leading to implicit constraints for confidence.

> > Thanks for your interest! In this work, the confidence maps are neat because we impose intermediate supervision on their corresponding depth maps respectively, leading to implicit constraints for...

Thanks for your interest Krik! You could change `args.val_h` and `args.val_w`. However, these values should be carefully set as the raw inputs are down-sampled 5 times in the model, which...

Thanks for your interest! I don't think our implementation is incorrect as when I naively test the follow script: ``` import torch d3_list = [i for i in range(4)] depth3...