I have been trying to create ResNet-18 on Julia. I have managed to create a functional one but it is slow and uses lot of GPU memory. This is puzzling since similar architecture on Tensorflow runs 5-10 times faster and uses much less memory. Also, there is a implementation of VGG-16, which I found t…

A implementation of ResNet-18 uses lot of GPU memory

CarloLucibello May 9, 2020, 5:50am 11

@OTapio could you open an issue on Flux?

Topic		Replies	Views
Memory challenges for Flux on Resnet Machine Learning gpu	8	1412	September 7, 2022
MNIST GPU CuArrays error GPU	23	3116	January 22, 2019
The same network performs differently in Flux.jl and tensorflow Machine Learning performance	13	3096	December 18, 2019
State of deep learning in Julia Machine Learning	18	15689	September 28, 2019
Flux's model-zoo CIFAR10 example saturates 8GB gpu General Usage gpu , flux	5	666	June 29, 2020