Anthony Blaom, PhD

icon indicating a website link ablaom.github.io icon indicating an email [email protected]

icon company University of Auckland icon location Auckland icon location Mathematician and Data Scientist, PhD Caltech • Expertise: Differential Geometry, Dynamical Systems, Fluid Mechanics, Statistics, Machine Learning, Julia

Results 815 comments of Anthony Blaom, PhD

Omnibus PR, including switch to explicit style differentiation

This PR is above average in complexity. This means a review is particularly important but it's also going to be more work than usual. @pat-alt Do you have any interest...

Omnibus PR, including switch to explicit style differentiation

@pat-alt Sorry to re-ping, but I'm not sure who else to ask for a review here. @tiemvanderdeure Would you consider reviewing? If possible, hoping for a merge in the next...

Omnibus PR, including switch to explicit style differentiation

Let's see if @pat-alt is able to finds some time.

Omnibus PR, including switch to explicit style differentiation

Thanks @pat-alt for your review. Much appreciated. I've made a few tweaks in response to the comments.

Omnibus PR, including switch to explicit style differentiation

@pat-alt How are we doing? Happy with the changes?

Omnibus PR, including switch to explicit style differentiation

Thanks @pat-alt for your review. 🙏🏾

How to use Metalhead'model as ImageClassifier model?

Thanks. Perhaps we can now resolve https://github.com/FluxML/MLJFlux.jl/issues/162! I'm happy to make MetalHead as a dependency of MLJFlux. PR welcome.

How to use Metalhead'model as ImageClassifier model?

Closed in favour of #205

deprecated warning in documentation

Good catch @rdavis120, thanks. That [doc string](https://github.com/FluxML/MLJFlux.jl/blob/4fa632de257cfde9dc0b01693b1f4270a4ecc405/src/types.jl#L697C51-L697C51) indeed requires updating.

Error when batch_size different from 1 in NeuralNetworkRegressor

Thanks @MathNog for reporting. I've not tried to reproduce, but your analysis sounds reasonable. (Current tests do include changing batch size for some non-recurrent networks.) Each time `MLJModelnterface.fit` is called,...