Joel-OPC comments

Repositories
Issues
Comments

Results 2 comments of


                                            Joel-OPC

"RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn" when using my loss-function

I got the same error but with the default QuantileLoss. Tested on: - pytorch-forecasting 0.9.1 - pytorch-lightning 1.4.8 - pytorch 1.9.1 Thank you for your help!

AttributeError: module 'tensorflow.python.eager.backprop' has no attribute '_record_gradient'

I got the same issue when using the DeepExplainer.