About the autograd category
|
|
0
|
3597
|
May 13, 2017
|
Parameters stuck at zero for custom layer
|
|
6
|
28
|
May 1, 2024
|
Custom gradients only for inputs that require grad
|
|
2
|
30
|
May 1, 2024
|
What does the function wrapper @once_differentiable do?
|
|
5
|
3496
|
May 1, 2024
|
In what situation does the decorator once_differentiable help?
|
|
3
|
47
|
May 1, 2024
|
2x slowdown when directly operating on parameter tensor in forward function
|
|
2
|
34
|
April 30, 2024
|
Compute gradient with respect to the input for high-dimensional output
|
|
1
|
28
|
April 30, 2024
|
Backprop through indices based on some operations
|
|
3
|
48
|
April 29, 2024
|
My network's weights get updated despite using torch.no_grad()
|
|
4
|
48
|
April 29, 2024
|
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [200, 2]], which is output 0 of AsStridedBackward0, is at version 1401; expected version 1400 instead
|
|
5
|
161
|
April 28, 2024
|
Is it safe to modify output's grad and return as input's grad?
|
|
6
|
61
|
April 28, 2024
|
How to concatenate feature vectors from different extractors inplace
|
|
0
|
30
|
April 27, 2024
|
How to make my faster GPU execute two batches while my other GPU does a batch?
|
|
0
|
36
|
April 26, 2024
|
`zero_grad` before `step` causes gradient explosion?
|
|
3
|
67
|
April 26, 2024
|
Meta learning weight update
|
|
0
|
32
|
April 26, 2024
|
Propagate gradient to parameters not directly involved in computation
|
|
9
|
175
|
April 25, 2024
|
Is it safe to set flag for single autograd.Function.backward call
|
|
3
|
58
|
April 24, 2024
|
Diverging gradients obtained through: 1) tensor.register_hook in a class vs 2) module.register_full_backward_hook outside of a class
|
|
0
|
218
|
April 24, 2024
|
Fixing the Training Function for an LSTM model built from scratch
|
|
4
|
59
|
April 24, 2024
|
What is the detailed operations of `torchfunc.jvp`
|
|
2
|
54
|
April 24, 2024
|
Getting gradients with respect to input features for a batched input
|
|
3
|
50
|
April 23, 2024
|
CUDA Out of Memory Error with jvp() in Large Model Training - Need Insights or Fixes
|
|
0
|
42
|
April 23, 2024
|
Mixing pytorch autograd with custom vjp for optimization
|
|
2
|
28
|
April 23, 2024
|
Loss.backward() call not updating loss
|
|
2
|
38
|
April 23, 2024
|
Out.backward() and weight access
|
|
1
|
37
|
April 23, 2024
|
Backpropagating w.r.t detached tensor
|
|
2
|
35
|
April 23, 2024
|
A question about autograd.Function
|
|
2
|
51
|
April 23, 2024
|
Backpropagate several error values
|
|
5
|
72
|
April 22, 2024
|
Finding the Diagonal of Hessian wrt Input for Vector-Valued Functions
|
|
1
|
53
|
April 21, 2024
|
Grad becomes nan for all parameters
|
|
7
|
107
|
April 20, 2024
|