AshPy is a TensorFlow 2.0 library for (distributed) training, evaluation, model selection, and fast prototyping. It is designed to ease the burden of setting up all the nuances of the architectures built to train complex custom deep learning models.

AshPy, why?

Ashpy provides already prepared trainers for classifier models and GANs. In particular, in regards of the latter, it offers a basic GAN sarchitecture with a Generator-Discriminator structure and an enhanced GAN architecture version made up of a Encoder-Generator-Discriminator structure. In general AshPy aims to:

  • Rapid model prototyping
  • Enforcement of best practices & API consistency
  • Remove duplicated and boilerplate code
  • General usability by new project

AshPy, where?

The first version of AshPy is available on PyPi, you can install it in your virtualenv with pip install ashpy.

Here some useful links:

AshPy is created and maintained primarily by the ML & CV Lab @ Zuru Tech. Please contact ml@zuru.tech for doubt, information or suggestions.