Hacker News Reader

Full thread

alok-g

Love this.

Am wondering how well this will work on Windows.

Likewise for the pretrained models on my personal laptop (i7, 32GB RAM, RTX 2060 6GB).

View on HN

Keras is meant for training, not inference.

I'm a bit of a novice in the space, if keras isn't for inference, what's the intended workflow?

Train with keras and then?

You can absolutely serve with Keras if your inference server is in Python. For instance, if you're looking for a basic solution, you can just set up a Flask app that calls `predict()` on a Keras model.

If you're looking for a high-performance solution that is entirely Python-free, then you can simply export your Keras model as a TF SavedModel and serve it via TFServing. TFServing is C++ based and works on both CPU and GPU.

Then there's standard formats like ONNX and inference on any platform or language or hardware that you prefer

I understand. I would like to train smaller proof-of-concept models on my laptop, which could build upon large pre-trained models though. Thanks.

Reply on news.ycombinator.com