George Pearse
George Pearse
Done some work in this area and really regret not having used cleanlab at the time! Just read this in the docs: > cleanlab’s module helps you deal with dataset-level...
I will replace the loading to yaml, with a pull of a docker image of the swagger UI (from docker hub). This docker-image would contain already contain the yaml spec,...
https://github.com/ElementAI/baal/blob/d2a31ff5f22b0279b2374e957d92039dbbd34e88/baal/active/__init__.py#L32
Composer have a brilliant dashboard (https://app.mosaicml.com/explorer/imagenet) which summarises all of their experiment results. It allows you to inspect results against some set of hyperparameters, understand some simple trends, and what...
Do any of the implementations of KNN within this repo extend to the multi-label case? That is to say, usable in the context of multi-object detection from neural network embeddings...
Feel like this could be made to be very easy to demo/test, if it were possible to run some of the core components (UI) as a docker image, and then...
Should it be reasonably easy to adapt your ML KNN implementation to use FAISS as the ANN engine?
Would be really great to be able to get a breakdown by hour. Impossible for me to work out when to publish at the minute. I would not be able...
I've had very limited luck with python local development on my m1 mac. Is there a way to run the code on a remote server but then have Blender run...
### Motivation Fast CV dataset visualisations in GCP notebooks ### What areas of FiftyOne does this feature affect? FiftyOne UI in notebook ### Details  The UI doesn't render in...