|
GPU backend-agnostic way to create efficiently random number on the GPU
|
|
2
|
52
|
February 20, 2025
|
|
Distributed Data Parallel training with 2 GPUs fails with Flux.jl on AMD GPUs
|
|
7
|
79
|
February 18, 2025
|
|
Save model when training with Distributed Data Parallel
|
|
0
|
28
|
February 11, 2025
|
|
Segfault using Flux + Intel integrated GPU
|
|
2
|
47
|
February 6, 2025
|
|
Help with CUDA and Flux. DeviceMemory issue
|
|
2
|
48
|
February 2, 2025
|
|
Gradient not being computed when training NN using Flux
|
|
3
|
87
|
January 30, 2025
|
|
Announcing TinyMachines.jl
|
|
0
|
330
|
January 17, 2025
|
|
Extremely high memory consumption on CPU
|
|
2
|
109
|
January 13, 2025
|
|
How to compute TanhExp / TeLU function accurately?
|
|
10
|
154
|
January 6, 2025
|
|
[pre-ANN] Differentiable FDTD for inverse design in photonics, acoustics and RF
|
|
53
|
4231
|
December 20, 2024
|
|
[ANN] Jello.jl - Manufacturable geometry generation for topology optimization & generative design
|
|
14
|
1763
|
December 19, 2024
|
|
How to implement a sparse decoder layer in Flux.jl?
|
|
1
|
67
|
December 17, 2024
|
|
"gpu_device" not defined in DDP with Flux
|
|
2
|
49
|
December 15, 2024
|
|
Memory usage increasing with each epoch
|
|
15
|
497
|
December 11, 2024
|
|
Cannot differentiate through a multivariate log normal probability density with Zygote
|
|
4
|
133
|
December 11, 2024
|
|
Flux and Metal circular dependencies in 1.10.7
|
|
2
|
92
|
December 11, 2024
|
|
Basic example for using Transformers.jl for sequential autoencoding
|
|
0
|
39
|
December 10, 2024
|
|
Sparse loss with Flux
|
|
3
|
64
|
December 9, 2024
|
|
AD Troubles in Flux and Unusual Loss
|
|
1
|
106
|
November 24, 2024
|
|
Downloading transformer weights
|
|
0
|
35
|
November 21, 2024
|
|
Kernel methods inside of Flux
|
|
1
|
111
|
November 20, 2024
|
|
Flux conv with GPU Arrays
|
|
5
|
104
|
November 12, 2024
|
|
Avoid allocation of a Flux model on the CPU
|
|
3
|
112
|
October 27, 2024
|
|
Custom Flux.jl Layer Not Updating (problem with Flux.trainable?)
|
|
2
|
195
|
October 19, 2024
|
|
How to create Dense with initialed weights in vector
|
|
0
|
31
|
October 14, 2024
|
|
Flux - sigmoid in last layer destroys learning?
|
|
13
|
182
|
October 11, 2024
|
|
Flux has no Lecun Normalization weight init function?
|
|
0
|
80
|
October 9, 2024
|
|
Flux: combine two neural networks to run simultaneously?
|
|
4
|
143
|
October 2, 2024
|
|
GraphNeuralNetworks.jl or GeometricFlux.jl
|
|
1
|
85
|
September 25, 2024
|
|
Flux slows down by 10x when moving from local system to high performance cluster
|
|
10
|
256
|
September 24, 2024
|