|
The right way to implement a residual network (ResNet)
|
|
2
|
1639
|
August 25, 2021
|
|
How to make parameters of function within Flux.Chain trainable?
|
|
2
|
865
|
August 25, 2021
|
|
Flux.Chain vs expand everything in a function
|
|
1
|
481
|
August 25, 2021
|
|
How to use multiple inputs in `NeuralODE` object?
|
|
2
|
733
|
August 25, 2021
|
|
Train neural ODE with mini-batch in different initial conditions
|
|
5
|
1444
|
August 25, 2021
|
|
neuralODE not using multiple CPUs
|
|
3
|
412
|
August 24, 2021
|
|
Computational performance when broadcasting a convolution layer
|
|
5
|
599
|
August 24, 2021
|
|
How to handle dataloader consisting of data with different dimensions?
|
|
3
|
789
|
August 23, 2021
|
|
Pytorch's Identity() implementation/alternative in Fluxml?
|
|
8
|
896
|
August 23, 2021
|
|
Flux.jl: params() and gradient() ocnfusion
|
|
4
|
705
|
August 23, 2021
|
|
ERROR: LoadError: ArgumentError: cannot take the CPU address of a CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}
|
|
12
|
1087
|
August 23, 2021
|
|
Where can i find documentation about Flux modular (approach) for building models?
|
|
4
|
464
|
August 21, 2021
|
|
Batch evaluation for NeuralODE?
|
|
1
|
1313
|
August 21, 2021
|
|
Interface for loading GBIF datasets into Flux
|
|
3
|
363
|
August 20, 2021
|
|
Flux running slow?
|
|
16
|
2903
|
August 19, 2021
|
|
Conv_mnist model-zoo example,
|
|
9
|
866
|
August 18, 2021
|
|
[Graph]CodeBERT; and e.g. (2- to) 8-bit int networks better than float, for Transformers/BERT
|
|
0
|
714
|
August 17, 2021
|
|
Connection between sensitivity algorithm and gradient calculation of the loss function
|
|
6
|
518
|
August 17, 2021
|
|
How to convert a JPEG image (from mobile) to a stantard 60k Array{ColorTypes.Gray{FixedPointNumbers.Normed{UInt8, 8}}, 2}) (from Flux.Data.MNIST)?
|
|
5
|
1052
|
August 17, 2021
|
|
Question on QSIR Model and Flux.train for COVID-19 SIR data
|
|
3
|
444
|
August 16, 2021
|
|
Flux question: best way to write a function that reuses some terms
|
|
1
|
311
|
August 16, 2021
|
|
Flux assumes only trainable parameters should be moved to GPU
|
|
3
|
1076
|
August 16, 2021
|
|
Horovod and Flux / Julia
|
|
7
|
1155
|
August 15, 2021
|
|
Combining multiple-shooting with out-of-ODE multithreading
|
|
1
|
542
|
August 13, 2021
|
|
AssertionError GCNConv FeaturedGraph GeometricFlux
|
|
1
|
306
|
August 13, 2021
|
|
Recent AI developments: Roformer (transformer w/Rotary Position Embedding) and DL to Rejuvenate Symbolic AI: Neural Production
|
|
4
|
1139
|
August 13, 2021
|
|
FeaturedGraph Explanation
|
|
0
|
284
|
August 12, 2021
|
|
Get training data from saved machine
|
|
1
|
359
|
August 11, 2021
|
|
NeuralODE: optimal control action in a constrained optimization problem
|
|
13
|
2181
|
July 26, 2021
|
|
Any implementation of 'Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs'?
|
|
2
|
505
|
August 6, 2021
|