Significantly Higher VRAM Usage and Slower Training on Flux Compared to PyTorch

It doesn’t produce native Julia models, but you can use it inside the rest of your native Julia model. Well, I suppose as long as you compile it to Reactant.jl.

Also see here, I’m working on a timm port for Lux.jl: [ANN] Jimm.jl: Lux ports of timm image backbones, with HuggingFace pretrained weights

It would likely be pretty easy to do the same sort of workflow I did here to port things over to Flux.jl, but I’m not personally familiar with it.