the problem is in " x_batch, y_batch = x_batch|>gpu, y_batch|>gpu " when i convert batches to gpu, removing it will work, but how can i make it work on gpu? pullback function from Zygote. here is fullcode using Flux using Zygote using CUDA using CSV using DataFrames using Images using MLDatasets u…

ERROR: LoadError: ArgumentError: cannot take the CPU address of a CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}

extremety1989 August 22, 2021, 3:19pm 11

thanks!

Topic		Replies	Views
Training with Flux.jl on the GPU causes ArgumentError: cannot take the CPU address of a CuArray GPU question , gpu , flux , machine-learning , neural-network	4	1123	May 28, 2022
Unable to save and load model (or parameters) with BSON either on GPU or CPU Machine Learning gpu , cuda , flux , bson	2	1270	July 15, 2021
Flux.jl: training fails at GPU but works on CPU Machine Learning gpu , flux	1	647	September 19, 2019
MNIST GPU CuArrays error GPU	23	3162	January 22, 2019
Flux: Scalar getindex error Machine Learning	13	2126	May 15, 2020