|
About the autograd category
|
|
0
|
3918
|
May 13, 2017
|
|
Is gradient flow lost when using Numpy?
|
|
3
|
13
|
April 15, 2025
|
|
Gradient computation performance
|
|
2
|
14
|
April 15, 2025
|
|
Autograd process isn't available when I profile via torch.profiler
|
|
3
|
15
|
April 15, 2025
|
|
Making autograd saved tensors hooks specific to certain arguments
|
|
7
|
28
|
April 14, 2025
|
|
How the autograd is implmented in pytorch
|
|
3
|
22
|
April 13, 2025
|
|
Custom autograd function breaking computation graph
|
|
2
|
20
|
April 10, 2025
|
|
Is grad_fn for a non-differentiable function that function's inverse?
|
|
1
|
27
|
April 9, 2025
|
|
Autograd FLOP Calculation with Higher Order Derivatives
|
|
2
|
77
|
April 9, 2025
|
|
Does tensor.register_post_accumulate_grad_hook() always fire once, or multiple times?
|
|
1
|
19
|
April 9, 2025
|
|
Selective gradient clipping
|
|
4
|
26
|
April 8, 2025
|
|
Is there a faster way to compute the jacobian than autograd.functional.jacobian?
|
|
4
|
45
|
April 7, 2025
|
|
Tackling Low GPU Kernel Occupancy During Loss Function Computation
|
|
1
|
25
|
April 7, 2025
|
|
Memory used by `autograd` when `torch.scatter` is involved
|
|
9
|
66
|
April 7, 2025
|
|
Is there a way to visualize the gradient path of the back propagation of the entire network
|
|
7
|
15179
|
April 4, 2025
|
|
Backward multiple forward passes
|
|
12
|
4458
|
April 3, 2025
|
|
Gradients calculations only till certain layer
|
|
3
|
15
|
April 2, 2025
|
|
Segmentation fault when calling .backward() after moving data to GPU (PyTorch + CUDA 12.1)
|
|
6
|
50
|
March 31, 2025
|
|
Pytorch autograd wrong values on Coriolis- & Centrifugal Matrix
|
|
0
|
14
|
March 25, 2025
|
|
Greedy optimisation with random noise in gradients
|
|
10
|
2412
|
March 24, 2025
|
|
Where does the ctx variable come from?
|
|
4
|
1007
|
March 21, 2025
|
|
Why does merging all loss in a batch make sense?
|
|
6
|
2194
|
March 21, 2025
|
|
Get softmax_lse value for sdpa kernel?
|
|
0
|
12
|
March 20, 2025
|
|
How to store temp variables with register_autograd without returning them as output?
|
|
1
|
34
|
March 19, 2025
|
|
CUDA memory issue in Hessian vector product
|
|
0
|
17
|
March 17, 2025
|
|
CUDA Memory Profiling: perculiar memory values
|
|
6
|
322
|
March 17, 2025
|
|
How to calculate Jacobians for a batch
|
|
5
|
56
|
March 16, 2025
|
|
Initializing tensor inside custom loss fn causes cuda memory err
|
|
5
|
45
|
March 12, 2025
|
|
Computing Gradient of Loss w.r.t Learning Rate
|
|
1
|
37
|
March 12, 2025
|
|
PINN for 2D Heat Conduction Always Converges to a Constant Solution
|
|
2
|
47
|
March 10, 2025
|