General PrinciplesΒΆ

Generally there are two things you can do with SimpleSR. You can either train models on a dataset, or you can evaluate already trained models on your test data.

For training you will need to:

  • Obtain a set of training images (links to some popular Super-Resolution data sets can be found here.

  • Initialize a DataPipeline with your training data

  • Initialize an SRModel - The SRModel needs a Generator - this the component that learns to upscale images - Optionally you can also provide a Discriminator to the SRModel to train in adversarial/GAN mode

  • finally you need to start the training process with the initiaized DataPipeline and SRModel

For evaluation you will need:

  • A DataPipeline initialized with your test images (initialized with evaluate_only=True)

  • The path to a saved model

See the examples folder for some training and evaluation examples and read the docs for training/evaluating models for further info.