Not able to use BatchNorm with track_stats=false on GPU. julia> using Flux julia> model = Chain(Dense(10,5),BatchNorm(5,relu; track_stats=false)) Chain(Dense(10, 5), BatchNorm(5, relu)) julia> modelgpu = gpu(model) Chain(Dense(10, 5), BatchNorm(5, relu)) julia> x = randn(Float32, 10, 100); juli…

BatchNorm: only track_stats=true supported on gpu

ymtoo May 31, 2021, 3:50am 3

Thanks for pointing out the functions of BatchNorm on GPU.

Topic		Replies	Views
Issue with Flux BatchNorm Machine Learning question , flux , machine-learning	2	542	June 18, 2023
Modifying Flux source code for GPU Specific Domains	4	212	March 27, 2023
Flux.train failing with CUDA GPU Machine Learning	5	924	March 27, 2019
MNIST GPU CuArrays error GPU	23	3157	January 22, 2019
BatchNorm gradient is inconsistent with PyTorch in training mode Machine Learning question , flux	2	865	December 18, 2020