Question

Optimizing an autograd + list comprehension python operation

score 24 · Answer 1 · 2024-03-27T07:59:32.047000

24

Views

Optimizing an autograd + list comprehension python operation

Published on 27 March 2024 at 07:59

score 31 · Answer 2 · 2024-03-23T22:35:54.593000

31

Views

SymPy - Can't calculate derivative wrt expression, is there an alternative for intermediate expressions?

Published on 23 March 2024 at 22:35

score 32 · Answer 3 · 2024-03-18T20:11:24.003000

32

Views

How to generate jacobian of a tensor-valued function using torch.autograd?

Published on 18 March 2024 at 20:11

score 26 · Answer 4 · 2024-03-11T08:09:23.270000

26

Views

Backprop two networks with different loss without retain_graph=True?

Published on 11 March 2024 at 08:09

score 53 · Answer 5 · 2024-03-06T14:37:08.313000

53

Views

Checking derivative tensor in Pytorch

Published on 06 March 2024 at 14:37

score 50 · Answer 6 · 2024-02-26T22:25:38.820000

50

Views

Rudimentary autograd implementation in Rust

Published on 26 February 2024 at 22:25

score 79 · Answer 7 · 2024-02-25T16:53:34.607000

79

Views

Calculating two gradients in pytorch and reusing an intermediate gradient

Published on 25 February 2024 at 16:53

score 18 · Answer 8 · 2024-02-21T11:27:07.557000

18

Views

Autograd "ValueError: setting an array element with a sequence" when computing norm.logpdf partial derivative

Published on 21 February 2024 at 11:27

score 90 · Answer 9 · 2024-02-20T23:41:28.660000

90

Views

JAX jax.grad on simple function that takes an array: `ConcretizationTypeError: Abstract tracer value encountered where concrete value is expected`

Published on 20 February 2024 at 23:41

score 42 · Answer 10 · 2024-02-12T20:33:28.147000

42

Views

Pytorch gradient accumulation implementation results in inplace operation error?

Published on 12 February 2024 at 20:33

score 118 · Answer 11 · 2024-02-08T05:17:32.927000

118

Views

Pruning nn.Linear weights inplace causes unexpected error, requires slightly weird workarounds. Need explanation

Published on 08 February 2024 at 05:17

score 37 · Answer 12 · 2024-02-06T01:25:44.017000

37

Views

PyTorch methods that can only be called from `forward`

Published on 06 February 2024 at 01:25

score 28 · Answer 13 · 2024-01-31T19:49:15.327000

28

Views

Pytorch: Compute gradient dx given Ax=b without solving the whole system

Published on 31 January 2024 at 19:49

score 58 · Answer 14 · 2024-01-29T04:18:59.317000

58

Views

Getting derivatives of NNs according to its inputs by batches in JAX

Published on 29 January 2024 at 04:18

score 24 · Answer 15 · 2024-01-25T01:47:50.630000

24

Views

How can I calculate the partial derivative using torch.autograd.grad() when the inputs and outputs are batched?

Published on 25 January 2024 at 01:47

score 60 · Answer 16 · 2024-01-23T06:24:13.640000

60

Views

Why Pytorch autograd returns 'None' and throws error without variable exponentiated

Published on 23 January 2024 at 06:24

score 107 · Answer 17 · 2023-12-28T07:59:49.243000

107

Views

LLaMA 2 training inplace operation

Published on 28 December 2023 at 07:59

score 109 · Answer 18 · 2023-12-12T12:15:55.070000

109

Views

Higher order derivatives w.r.t. singular feature map in CNN architecture using PyTorch

Published on 12 December 2023 at 12:15

score 81 · Answer 19 · 2023-12-06T16:29:10.600000

81

Views

Pytorch compute gradients without autograd with respect to weights

Published on 06 December 2023 at 16:29

score 215 · Answer 20 · 2023-12-03T21:12:46.103000

215

Views

Print intermediate gradient values during backward pass in Pytorch using hooks

Published on 03 December 2023 at 21:12

List Question

Optimizing an autograd + list comprehension python operation

SymPy - Can't calculate derivative wrt expression, is there an alternative for intermediate expressions?

How to generate jacobian of a tensor-valued function using torch.autograd?

Backprop two networks with different loss without retain_graph=True?

Checking derivative tensor in Pytorch

Rudimentary autograd implementation in Rust

Calculating two gradients in pytorch and reusing an intermediate gradient

Autograd "ValueError: setting an array element with a sequence" when computing norm.logpdf partial derivative

JAX jax.grad on simple function that takes an array: `ConcretizationTypeError: Abstract tracer value encountered where concrete value is expected`

Pytorch gradient accumulation implementation results in inplace operation error?

Pruning nn.Linear weights inplace causes unexpected error, requires slightly weird workarounds. Need explanation

PyTorch methods that can only be called from `forward`

Pytorch: Compute gradient dx given Ax=b without solving the whole system

Getting derivatives of NNs according to its inputs by batches in JAX

How can I calculate the partial derivative using torch.autograd.grad() when the inputs and outputs are batched?

Why Pytorch autograd returns 'None' and throws error without variable exponentiated

LLaMA 2 training inplace operation

Higher order derivatives w.r.t. singular feature map in CNN architecture using PyTorch

Pytorch compute gradients without autograd with respect to weights

Print intermediate gradient values during backward pass in Pytorch using hooks

Trending Questions

Popular # Hahtags

Popular Questions