autograd


Topic Replies Activity
Unable to find gradient for Tensor 5 January 13, 2020
RuntimeError: element 0 of variables does not require grad and does not have a grad_fn 16 January 13, 2020
Info about binary cross entropy with logits 3 January 13, 2020
RuntimeError: derivative for _thnn_fused_gru_cell_backward is not implemented 6 January 13, 2020
Is there any work around to make a differentiable torch.max? 1 January 11, 2020
CUDA Out of memory when using autogrid to do multiple round of back propagation 1 January 11, 2020
Between-class label 3 January 11, 2020
Custom loss function: gradients are None 12 January 10, 2020
Rbfn: Getting same result in each epoch 9 January 9, 2020
Pytorch 0.4.1 getting gradient at a particular node 7 September 7, 2018
Is hidden_state in place operation as shown in this example? 4 January 9, 2020
Is this the correct way? 2 January 9, 2020
How to predict the derivation of the output? 3 January 9, 2020
`torch.cuda.current_device()` always return 0 16 January 9, 2020
Testing and Confidence score of Network trained with nn.CrossEntropyLoss() 1 January 8, 2020
Understanding last_epoch usage in optim.lr_scheduler.CyclicLR 2 January 8, 2020
Will BatchNorm2d become InstanceNorm2d when batch size is 1? 2 January 7, 2020
Problems on getting the hessian vector product of a network 2 January 7, 2020
Custom autograd function with Int tensor input 5 January 7, 2020
The gradients assignment for torch.cat() seems confusing? 4 January 7, 2020
`torch.cdist` cannot handle large matrix on GPU 4 January 7, 2020
Batchnorm and back-propagation 7 January 7, 2020
Recording gradients in RNNs at each point in time 8 January 6, 2020
Backprop from Parameter.grad 8 January 6, 2020
How to calculate 2nd derivative of a likelihood function 22 January 6, 2020
CUDA Invalid Configuration Error on GPU Only 13 January 6, 2020
Polygamma(n,x) is not implemented for n>=2 at /pytorch/aten/src/THC/generic/THCTensorMathPointwise.cu:364 1 January 6, 2020
[Hessian Vector Product] RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior 6 January 6, 2020
Autograd of scatter 2 January 6, 2020
Profiling with Utils.bottleneck error: unqualified exec with nested function 3 January 5, 2020