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

Iulian.Cioarca March 27, 2020, 6:40pm 9

Julia 1.4, Flux 0.10.3. I did not explicitly install CuArrays since I don’t need it, but the version added by Flux is 1.7.0.

Topic		Replies	Views
Memory challenges for Flux on Resnet Machine Learning gpu	8	1370	September 7, 2022
Flux + GPU memory problems Machine Learning flux	2	817	April 26, 2022
Flux memory usage high in SRCNN Machine Learning	3	192	June 5, 2024
Flux runs out of memory Machine Learning memory-allocation , flux	25	4298	June 1, 2023
Memory usage increasing with each epoch Machine Learning cuda , flux	18	699	April 14, 2025