|
Differentiating With Respect to Learning Rate
|
|
3
|
106
|
February 12, 2025
|
|
Calling autograd.Function in autograd.Function
|
|
4
|
78
|
February 11, 2025
|
|
About torch.autograd.set_detect_anomaly(True):
|
|
5
|
25566
|
February 10, 2025
|
|
Vmap over autograd.grad of a nn.Module
|
|
6
|
1036
|
February 10, 2025
|
|
Is_grads_batched
|
|
3
|
2621
|
February 8, 2025
|
|
Error: Implementing Custom Activation Function(TERLU) using this paper https://arxiv.org/pdf/2006.02797
|
|
1
|
80
|
February 7, 2025
|
|
Question about the Extending PyTorch tutorial
|
|
1
|
18
|
February 7, 2025
|
|
How to reduce the for loop with torch.einsum function?
|
|
1
|
34
|
February 7, 2025
|
|
Freezing CNN Channels
|
|
2
|
113
|
February 7, 2025
|
|
Softmax returning only 0 and 1
|
|
1
|
35
|
January 28, 2025
|
|
Gradcheck fails for custom activation function
|
|
3
|
58
|
January 26, 2025
|
|
Missing argument create_graph in torch.func api
|
|
6
|
158
|
January 24, 2025
|
|
Backward pass error for loss computation in loop
|
|
1
|
28
|
January 23, 2025
|
|
.grad should not equal None here
|
|
3
|
129
|
January 23, 2025
|
|
Unexpected behavior when using torch.autograd.functional.jacobian with multiple inputs/outputs neural network
|
|
3
|
34
|
January 21, 2025
|
|
Loss.backward() called after torch.nograd()
|
|
4
|
46
|
January 19, 2025
|
|
Where is the actual code for LayerNorm (torch.nn.functional.layer_norm)
|
|
6
|
4116
|
January 17, 2025
|
|
Why is requires_grad==False after multiplication?
|
|
9
|
581
|
January 16, 2025
|
|
Is it possible to have trainable module parameters in between static layer weights?
|
|
1
|
17
|
January 14, 2025
|
|
Torch.autograd.grad and masking issue
|
|
0
|
39
|
January 14, 2025
|
|
Unexpected behavior when using batch_jacobian with multiple inputs/outputs in quantum-classical neural network
|
|
2
|
43
|
January 12, 2025
|
|
Get a non-leaf tensor grad to its output
|
|
1
|
20
|
January 9, 2025
|
|
How to apply vmap on a heterogeneous tensor
|
|
5
|
118
|
January 6, 2025
|
|
How to figure out why my backwards pass is so slow?
|
|
2
|
130
|
January 6, 2025
|
|
How to remove backpropagation for specific tokens from the output of a transformer decoder only?
|
|
7
|
70
|
January 6, 2025
|
|
How does Pytorch Backward functions handle batched inputs?
|
|
4
|
96
|
January 4, 2025
|
|
Why the gradient values seems to be reversed in Tensor.backward()
|
|
9
|
20
|
January 2, 2025
|
|
Help with Projecting Gradients onto a Hypersphere's Tangent Plane
|
|
4
|
55
|
January 1, 2025
|
|
Autograd failing for sparse matmul at half precision
|
|
2
|
36
|
December 31, 2024
|
|
Custom layer-specific gradient calculation
|
|
1
|
94
|
December 31, 2024
|