search

DeepLearningDTU / 02456-deep-learning-with-PyTorch

Exercises and supplementary material for the deep learning course 02456 using PyTorch.
313 stars 455 forks source link

Use of word "equivalence" in backward #3

Open muthissar opened 6 years ago

muthissar commented 6 years ago

In https://github.com/DeepLearningDTU/02456-deep-learning-with-PyTorch/blob/master/1_Feedforward/1.2-automatic-differentiation.ipynb?short_path=5da64dc#L179, it says that the two statements are equivalent, however you cannot switch the two and run out.backward(torch.Tensor([1.0])).

Faur commented 6 years ago

This has probably been changed in a more recent version of PyTorch. We will have a look, thank you.