|
About the autograd category
|
|
0
|
3976
|
May 13, 2017
|
|
Nested forward mode AD not supported (jacobian)— what operations can trigger this?
|
|
1
|
13
|
July 28, 2025
|
|
Verifying grad_x after autograd double backprop
|
|
1
|
22
|
July 24, 2025
|
|
Custom Physics-Informed Loss Function Not Converging for PINN Thermodynamics Model
|
|
0
|
29
|
July 22, 2025
|
|
Can't vmap autograd.grad over outputs
|
|
10
|
132
|
July 16, 2025
|
|
Autograd function returns tensor views
|
|
1
|
35
|
July 16, 2025
|
|
Backward through the graph a second time
|
|
2
|
44
|
July 12, 2025
|
|
LSTM model weight gradients are all zero
|
|
3
|
36
|
July 11, 2025
|
|
Custom loss and its gradient
|
|
1
|
31
|
July 10, 2025
|
|
Why does autograd.backward go one edge further than `inputs`?
|
|
3
|
43
|
July 8, 2025
|
|
Implementing calculation of the Laplacian
|
|
6
|
5235
|
July 7, 2025
|
|
Efficient Computation of Second-Order Gradients
|
|
1
|
28
|
July 7, 2025
|
|
Tensor hooks for gradients from each path in the autograd graph
|
|
4
|
63
|
July 5, 2025
|
|
Memory bloat in gradient descent model
|
|
4
|
64
|
July 2, 2025
|
|
In-place modification in backward not allowed with torch.compile
|
|
1
|
20
|
July 1, 2025
|
|
Multi-discriminator GAN: No inf checks were recorded for this optimizer
|
|
2
|
30
|
June 25, 2025
|
|
Variable versioning error at backward
|
|
1
|
30
|
June 21, 2025
|
|
How to know if gradients backpropagate through a pytorch function?
|
|
1
|
547
|
June 20, 2025
|
|
How pytorch treat with inplace operation in backward
|
|
1
|
47
|
June 17, 2025
|
|
[SDPA] RTX5080 is different from CPU calculation result in backward with long seq
|
|
0
|
24
|
June 17, 2025
|
|
[BUG] RTX5080： Function 'MmBackward0' returned nan values in its 0th output.
|
|
2
|
38
|
June 16, 2025
|
|
Broken autograd momentum link
|
|
1
|
34
|
June 16, 2025
|
|
JVP and checkpointing
|
|
1
|
46
|
June 16, 2025
|
|
Constant Predictions in Non-Linear Model Despite Training Progress
|
|
2
|
41
|
June 15, 2025
|
|
Loss.backward(): element 0 of tensors does not require grad and does not have a grad_fn
|
|
6
|
2066
|
June 15, 2025
|
|
Custom autograd.Function for quantized C++ simulator
|
|
2
|
33
|
June 13, 2025
|
|
Evaluating gradients of output variables w.r.t parameters for pixelwise models
|
|
2
|
41
|
June 12, 2025
|
|
Error 'Output 0 is independent of input 0' happens while using jacobian of a function that the output changes in my demo with different input
|
|
2
|
37
|
June 11, 2025
|
|
How to obtain the variable asociation relationship of FX graph between forward and backward?
|
|
3
|
33
|
June 11, 2025
|
|
How do pytorch deal with the sparse jacobian matrix in jvp/vjp during autograd?
|
|
1
|
676
|
June 9, 2025
|