Autograd problem with tensors generated by torch.arange
|
|
5
|
69
|
April 9, 2024
|
Customized loss function lost grad_fn
|
|
1
|
47
|
April 9, 2024
|
Using torch.logical_and turns requires_grad flag to False
|
|
1
|
35
|
April 9, 2024
|
Gradient Reversal on data of a specific class
|
|
2
|
76
|
April 9, 2024
|
2 phase training of autoencoders (e.g. USAD, TranAD)
|
|
1
|
36
|
April 9, 2024
|
Using hook functions to call on a custom function to modify a layer given parameters of another layer
|
|
1
|
39
|
April 8, 2024
|
Trying to understand the gradient for softmax (without CrossEntropyLoss)
|
|
6
|
141
|
April 8, 2024
|
Modifying a Tensor with requires_grad=True in PyTorch - Maintaining Connection for Backpropagation
|
|
2
|
76
|
April 8, 2024
|
Remove Computation in Forward & Backward Pass
|
|
0
|
47
|
April 8, 2024
|
Non differentiability of complete QR decomposition for case where rows > columns
|
|
5
|
99
|
April 7, 2024
|
Can the new functional autograd take batches? Also, is it more efficient to compute a hessian with the new functional autograd than it is using the old autograd?
|
|
17
|
1990
|
April 7, 2024
|
Weighted Multi-label Focal Loss Implementation
|
|
0
|
59
|
April 6, 2024
|
Focal loss for imbalanced multi class classification in Pytorch
|
|
14
|
21699
|
April 6, 2024
|
RuntimeError: tensor does not have a device - which tensor?
|
|
3
|
71
|
April 5, 2024
|
Training two models simultaniously: incorrect backpropagation
|
|
1
|
83
|
April 4, 2024
|
RuntimeError: derivative for aten::_scaled_dot_product is not implemented
|
|
0
|
47
|
April 4, 2024
|
Autograd derivatives of multioutput ANN
|
|
2
|
90
|
April 4, 2024
|
Can PyTorch move a tensor along with its computational graph from GPU to CPU, and then move it back to GPU for backpropagation?
|
|
2
|
73
|
April 4, 2024
|
Unexpected error when performing backpropagation : "RuntimeError: self must be a matrix"
|
|
4
|
81
|
April 3, 2024
|
More efficient norm of gradient computations using vmap
|
|
0
|
48
|
April 3, 2024
|
Loss doesn't change PINN implementation of RLC equation
|
|
0
|
51
|
April 2, 2024
|
How to root cause - torch/autograd/__init__.py:xxx: UserWarning: Error detected in GeluBackward0. Traceback of forward call that caused the error
|
|
2
|
83
|
March 31, 2024
|
Why does ignore_index ignore the entire example and not the class?
|
|
1
|
67
|
March 30, 2024
|
Computing Hessian
|
|
1
|
88
|
March 30, 2024
|
Different size for tensor grad compared to the tensor itself
|
|
4
|
104
|
March 29, 2024
|
Multiple inputs in shared weight layers
|
|
1
|
82
|
March 28, 2024
|
Restricting output range in last layer of deep architecture [regression task]
|
|
1
|
62
|
March 27, 2024
|
More efficient autograd for matrix w.r.t matrix gradient computation?
|
|
0
|
58
|
March 27, 2024
|
Modifying intermediate layer output using Hooks
|
|
4
|
103
|
March 27, 2024
|
Loss becomes NaN when introducing regularization
|
|
0
|
83
|
March 26, 2024
|