Closed Etienne66 closed 2 years ago
Thank you for your contribution, this is great!
Not a problem. I've been trying to evaluate the pre-trained model. The numbers I'm getting are better than the original but I'm pretty sure I'm doing it correctly. Working on retraining it to see if I can get it to do better like they did for PWC-Net+
You might find this interesting: https://github.com/sniklaus/pytorch-pwc/issues/23
This fixes issue #47 and allows Tensorboard's
SummaryWriter.add_graph
to work although there are some TracerWarnings.The problem was that the trace injects tensors into the
correlation
functions and in this case it was putting the wordtensor
in the Cupy code when the string replace was being done.ie:
instead of:
The following warning still occurs but it seems it can be ignored as they are all in the
correlation
function and it couldn't be shown in the model anyway.TracerWarning: Converting a tensor to a Python number might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!