chrischute comments

Repositories
Issues
Comments

Results 3 comments of


                                            chrischute

why in my model_search only loss.backward(retain_graph=True) can run

If you're searching for an RNN cell, you are likely backpropagating all the way back through time ([relevant comment](https://github.com/quark0/darts/blob/master/rnn/train_search.py#L201-L202)). Try changing `repackage_hidden` in `rnn/utils.py` to this: ```python def repackage_hidden(h): if...

Autograd error: Inplace operations modify variable needed for gradient computations.

You could try changing that line to `x[:, :, z_idx] = x[:, :, z_idx] + z`. Still I'm not sure why you'd run into this, since I never saw it...

Autograd error: Inplace operations modify variable needed for gradient computations.

Yes, GPU utilization is low with this checkerboard strategy, but I used it to preserve memory. This assignment strategy uses less memory compared to multiplying with a mask. Flow++ is...