Replies: 4 comments 6 replies
-
Did you profile? |
Beta Was this translation helpful? Give feedback.
-
I uploaded the code here -> https://github.com/K1T00/TorchSharpUnet |
Beta Was this translation helpful? Give feedback.
-
Moving the using var d = torch.NewDisposeScope(); into my train/validate functions did a great speedup. I guess my issue is solved now :) |
Beta Was this translation helpful? Give feedback.
-
I have another question. Let’s say I have two datasets, with pytorch I could do: trainSet1 = MyCustomDataset(…) How can I combine datasets with TorchSharp? |
Beta Was this translation helpful? Give feedback.
-
Currently I’m trying to port this U-Net example https://github.com/Mostafa-wael/U-Net-in-PyTorch to TorchSharp. My results look comparable to the PyTorch example but training in TorchSharp is waaay slower. At least 10x slower. Same model, same batch size, images etc.
Anyone tried something similar and had more success?
Beta Was this translation helpful? Give feedback.
All reactions