In browser inference support

[AmitMY]

Thanks for this toolkit,
Is there any setting for which one would be able to create a model file that is executable inside the browser?
(for Tensorflow repositories, this would be Keras Layers or tflite models, for example)

[salvacarrion]

This library handles the preprocessing, training, and evaluation for you, without imposing any specific architecture. Therefore, you should be able to use the model of your choice such as a "lite-model4browser" (as long as it is a PyTorch one).

Ps. Keep in mind that it is in a very early stage of development (1-month-old)