I have a specific computer vision problem that I want to try solving using some pre-trained models. The Flux.jl docs don't actually have any pre-trained models in them like some of the other ML frameworks (PyTorch as an example). How would I access those sort of pertained models in Flux?
Asked
Active
Viewed 168 times
2
-
1If there is something unclear in the Flux.jl documentation that you would like to see changed, can you [file an issue](https://github.com/FluxML/Flux.jl/issues) with the project or [issue a pull request](https://github.com/FluxML/Flux.jl/pulls)? – PaSTE Jul 11 '21 at 13:06
1 Answers
3
In the Flux ecosystem, the functionality for something like pre-trained computer vision models has been extrapolated out into a separate package called MetalHead.jl: https://github.com/FluxML/Metalhead.jl
Per the docs there, you can create a VGG19 model by doing:
julia> vgg19 = VGG19()
VGG19()
and then you can pass the model to something like the classify
function along with an input image for a validation test.

logankilpatrick
- 13,148
- 7
- 44
- 125