A collection of models and utilities for the development of edge deployable Keras models
A library to help with the development of AI models with Keras, with a focus on edge / IoT applications. Based originally on https://github.com/yingkaisha/keras-unet-collection (see the [README.md](https://github.com/waterviewsrl/swiss-army-keras/blob/main/README-keras-unet-collection.md))
This library wants you to focus on dataset, model architecture and hyperparameters tuning, without worring about the rest.
It provides several helper classes which help in the development of CNN based AI models for edge IoT applications, where resources are limited and model quantization is reccomended.
The main features of the library are the following:
Training driver with builtin callbacks, configurable backbone unfreezing, and quantized model generation
Helper classes to easiliy combine pretrained backbones for Edge AI applications with the desired segmentation and classification architectures
Additional loss functions and optimizers which are not part of the Keras distribution, as for now
tensorflow>=2.4.1 (cpu or gpu) must be installed.
Install the dependency git+https://github.com/waterviewsrl/efficientnet-lite-keras.git (forked from [sebastian-sz/efficientnet-lite-keras](https://github.com/sebastian-sz/efficientnet-lite-keras) to simplify requirements and solve minor import issues):
pip3 install git+https://github.com/waterviewsrl/efficientnet-lite-keras.git
### Install with pip
You can install directly by pypi with pip:
pip3 install swiss-army-keras
You can find documentation and examples [here](https://swiss-army-keras.readthedocs.io/en/latest/index.html)
Example jupyter notebooks can also be found in the example folder here.
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Hashes for swiss_army_keras-0.10.0-py3-none-any.whl