How to save and use a trained neural network developed in PyTorch / TensorFlow / Keras?

Question

Are there ways to save a model after training and sharing just the model with others? Like a regular script? Since the network is a collection of float matrices, is it possible to just extract these trained weights and run it on new data to make predictions, instead of requiring the users to install these frameworks too? I am new to these frameworks and will make any clarifications as needed.

Answer 1

PyTorch: As explained in this post, you can save a model's parameters as a dictionary, or load a dictionary to set your model's parameters. You can also save/load a PyTorch model as an object. Both procedures require the user to have at least one tensor computation framework installed, e.g. for efficient matrix multiplication.