Narayan Schütz, PhD

Results 3 comments of Narayan Schütz, PhD

If anyone stumbles across this, it's a version problem, see here: https://discuss.pytorch.org/t/how-to-fix-mismatch-in-shape-when-using-backward-function/58865. The solution seems to be to replace `torch.FloatTensor([1])` with `torch.tensor(1, dtype=torch.float)` This will also introduce a few further...

This actually is one of the more annoying shortcomings of EDF in practice. Happens so very often. Would there be any way to fix it (I assume it is primarily...

@JiahaoPlus, I dont remember the exact error but it is basically an API version mismatch, where those versions would not match the interface of the affected functions or methods, so...