https://github.com/ElPapi42/DeepBay

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation
https://github.com/ElPapi42/DeepBay

Last synced: 3 months ago
JSON representation

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation

• Host: GitHub
• URL: https://github.com/ElPapi42/DeepBay
• Owner: elpapi42
• License: mit
• Created: 2019-10-24T20:21:45.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2019-12-22T14:29:05.000Z (almost 5 years ago)
• Last Synced: 2024-04-23T19:24:56.107Z (7 months ago)
• Language: Python
• Homepage: https://pypi.org/project/deepbay/
• Size: 65.4 KB
• Stars: 4
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow - DeepBay - High-Level Keras Complement for implement common architectures stacks, served as easy to use plug-n-play modules (Libraries)
• fucking-awesome-tensorflow - DeepBay - High-Level Keras Complement for implement common architectures stacks, served as easy to use plug-n-play modules (Libraries)

README

        
[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)

[![Development Status](https://github.com/ElPapi42/DeepBay/workflows/build/badge.svg?branch=development)](https://github.com/ElPapi42/DeepBay/actions?query=workflow%3A%22Test+Package%22)

[![GitHub version](https://badge.fury.io/gh/Elpapi42%2FDeepBay.svg)](https://badge.fury.io/gh/Elpapi42%2FDeepBay)

[![Last Commit](https://badgen.net/github/last-commit/ElPapi42/DeepBay)](https://github.com/ElPapi42/DeepBay/graphs/commit-activity)

# DeepBay

This project was created with the objective of compile Machine Learning Architectures created using Tensorflow or Keras. The architectures must be provided as a ready-to-use Plug-and-Play module that can be easily integrated into any existing project or architecture design.

## Installation

You can use pip for install this from [PyPi](https://pypi.org/project/deepbay/):

```

pip install deepbay

```

## Quick Start

You can use any architecture inside deepbay as an self-contained model ready to be trained:

```python

import tensorflow as tf

import deepbay

denseblock = deepbay.DenseBlock(units=1)

```

Or you can integrate it to any existing architecture, just use it as any other keras layer:

```python

import tensorflow as tf

import deepbay

model = tf.keras.models.Sequential()

model.add(deepbay.DenseBlock(units=1))

```

Keep an eye on input/output shapes, you can found them in the class documentation inside every module