Tasin comments

Repositories
Issues
Comments

Results 5 comments of


                                            Tasin

RuntimeError: output with shape [1, 256, 192] doesn't match the broadcast shape [3, 256, 192]

I had this problem before but on a different repository. I fixed it by using a specific version of PyTorch. Use pytorch 0.4.1 and torchvision 0.2.1

Distributed Training Mode

I have only modified the `train.py` line 178 - 196 so that it works with my own custom dataset.

Large GPU memory consumption at the beginning of training

I am experiencing the same problem. For a single forward pass, it consumes 46GB VRAM. Inference takes less than 8GB. What is the solution to this?

about model released？

what is the latest news?

processed data

> Hi, you can download data form this link. https://competitions.codalab.org/competitions/23471 The MPV dataset. The dataset has been removed. Can you please reupload it?