About the autograd category
|
|
0
|
3587
|
May 13, 2017
|
Propagate gradient to parameters not directly involved in computation
|
|
7
|
151
|
April 24, 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
|
|
2
|
39
|
April 24, 2024
|
Is it safe to set flag for single autograd.Function.backward call
|
|
2
|
38
|
April 24, 2024
|
Fixing the Training Function for an LSTM model built from scratch
|
|
4
|
36
|
April 24, 2024
|
What is the detailed operations of `torchfunc.jvp`
|
|
2
|
45
|
April 24, 2024
|
Getting gradients with respect to input features for a batched input
|
|
3
|
24
|
April 23, 2024
|
CUDA Out of Memory Error with jvp() in Large Model Training - Need Insights or Fixes
|
|
0
|
21
|
April 23, 2024
|
Mixing pytorch autograd with custom vjp for optimization
|
|
2
|
20
|
April 23, 2024
|
Loss.backward() call not updating loss
|
|
2
|
23
|
April 23, 2024
|
Out.backward() and weight access
|
|
1
|
24
|
April 23, 2024
|
Backpropagating w.r.t detached tensor
|
|
2
|
22
|
April 23, 2024
|
A question about autograd.Function
|
|
2
|
38
|
April 23, 2024
|
Backpropagate several error values
|
|
5
|
58
|
April 22, 2024
|
Finding the Diagonal of Hessian wrt Input for Vector-Valued Functions
|
|
1
|
43
|
April 21, 2024
|
Grad becomes nan for all parameters
|
|
7
|
97
|
April 20, 2024
|
How do I get `torch.onnx.export` to work with `aot_module`?
|
|
1
|
41
|
April 19, 2024
|
Differences between 'params.grad' and 'params.grad.data'
|
|
1
|
35
|
April 19, 2024
|
Model forward slows down when disabling gradients
|
|
5
|
79
|
April 19, 2024
|
Signed distance transform computation of predicted segmentation
|
|
6
|
4202
|
April 19, 2024
|
Intuition Behind Nesterov Update Rule for SGD w/ Momentum
|
|
0
|
37
|
April 19, 2024
|
Omit loss.backward for forward-only algos?
|
|
2
|
53
|
April 18, 2024
|
Set a portion of a tensor to have requires_grad=False
|
|
9
|
1406
|
April 18, 2024
|
Is there a way of accessing grad from other parameters in torch.optim.Optimiter.step() function?
|
|
2
|
39
|
April 18, 2024
|
OOM memory due to computation graph when stacking embeddings
|
|
2
|
51
|
April 17, 2024
|
How do I pass a forward value to a backward function
|
|
1
|
46
|
April 17, 2024
|
What would be a proper way of implementing this riemann gradient?
|
|
0
|
40
|
April 16, 2024
|
Backward on scatter_reduce raising an error
|
|
2
|
49
|
April 16, 2024
|
Skip gradient propagation if gradients less than a threshold
|
|
4
|
82
|
April 16, 2024
|
Linear solver for sparse matrices
|
|
5
|
88
|
April 16, 2024
|