ReverseDiff - differentiating with respect to some parameters but not others
|
|
6
|
462
|
July 18, 2022
|
Zygote and SDE failure: cannot differentiate through Lux NN
|
|
5
|
628
|
July 14, 2022
|
Taking the derivative of a scalar loss, that involves a gradient inside, errors on GPU only
|
|
7
|
761
|
July 13, 2022
|
Hypernetworks using Flux.destructure?
|
|
10
|
790
|
July 11, 2022
|
Flux/Lux - Combining two neural networks
|
|
1
|
710
|
July 7, 2022
|
Flux: Obtaining individual layer output for DenseNet from Metalhead.jl
|
|
2
|
591
|
July 6, 2022
|
How to "maximize" an unknown categorical function?
|
|
8
|
452
|
July 5, 2022
|
Errors when trying to compute hessian of flux neural net and jacobian of jacobian with zygote
|
|
1
|
368
|
July 4, 2022
|
Sparse jacobians of matrix models
|
|
37
|
1748
|
July 3, 2022
|
Saving and Loading Error BSON.jl
|
|
4
|
435
|
July 2, 2022
|
Spatial transformer (i.e. GPU-friendly interpolations with gradients) with Flux.jl?
|
|
7
|
884
|
July 1, 2022
|
Looking for collaborators - implementing SLIDE in julia
|
|
12
|
548
|
June 29, 2022
|
Pytorch clamp method in Julia?
|
|
4
|
449
|
June 27, 2022
|
Looking for pytorch method alternative in flux
|
|
5
|
355
|
June 26, 2022
|
Attempting to reimplement SRGAN from Pytorch to Flux, any help appreciated
|
|
4
|
1043
|
June 26, 2022
|
Pullback for both Flux model's inputs and parameters
|
|
9
|
797
|
June 26, 2022
|
Right way of applying `inverse_transform`
|
|
3
|
1194
|
June 25, 2022
|
(Flux) certain arbitrary model sizes and random seeds make gradients exactly zero
|
|
3
|
666
|
June 25, 2022
|
Simultaneous training of multiple neural networks with Lux
|
|
5
|
1152
|
June 25, 2022
|
Package for clustering data points
|
|
8
|
658
|
June 23, 2022
|
Using a variable graph structure with NeuralODE and GCNConv
|
|
3
|
685
|
June 22, 2022
|
How do I can I selectively inspect and use learned parameters in an MLJ pipeline?
|
|
1
|
331
|
June 20, 2022
|
How to find jacobian of learnt neural network model
|
|
1
|
397
|
June 19, 2022
|
Is it possible to train sparse neural networks in GPU?
|
|
3
|
501
|
June 17, 2022
|
Re-using layers in Flux.jl: how to train a multi-layer model sharing a common LSTM layer and separate dense layers?
|
|
1
|
612
|
June 15, 2022
|
Way to write the integral with ModelingToolkit
|
|
7
|
626
|
June 13, 2022
|
A minimal CUDA-compatible and differentiable GP implementation
|
|
11
|
1077
|
June 9, 2022
|
Dispatch on the last layer type in Flux
|
|
3
|
351
|
June 9, 2022
|
How to retrieve gradient value in custom Flux training loop?
|
|
3
|
384
|
June 8, 2022
|
Feature selection+classification pipeline
|
|
3
|
639
|
June 7, 2022
|