Skip to main content

Simple Python Framework for creating GANs and seeing evolution through time

Project description

PyGANs (Machine Learning Framework)

Python Framework for Generative Adversarial Networks. It provides an Abstraction layer to create and train GANs with an integrated monitoring module to see the evolution of the Network through time.

There are incorporated examples that show the usage of the framework in 2D functions and generating Hand Written Digits.

Tested Models:

  • Trigonometric Functions (f(x)=sin(x))
  • Polynomial Functions, for example:
    O f(x) = x**2
    O f(x) = x**5 - 3x**2 - 4
  • HandWritten Digits (MNIST)

Installation

PyGANs is available in the Python Package Index (PyPI), so it's possible to install it using the package installer for Python (pip), which install automatically the external dependencies:

$ pip install pygans

External Dependencies

If you install the library using pip, it will install automatically the dependencies.

  • Keras
  • Tensorflow
  • Numpy
  • Matplotlib

Versions

2.0.3

BugFix: Random Generation in Dataset_Generator_2D

2.0.2

  • BugFix: MNIST Animation

2.0.0

  • MNIST Supported
  • Simplified API
  • Optimizing training process
  • BugFix: Latent points generation on Standard normal distribution

1.0.0

  • 2D Functions tested
  • 2D animation supported

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pygans-2.0.3.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

pygans-2.0.3-py3-none-any.whl (8.2 kB view details)

Uploaded Python 3

File details

Details for the file pygans-2.0.3.tar.gz.

File metadata

  • Download URL: pygans-2.0.3.tar.gz
  • Upload date:
  • Size: 4.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.6.0.post20191030 requests-toolbelt/0.9.1 tqdm/4.40.0 CPython/3.7.5

File hashes

Hashes for pygans-2.0.3.tar.gz
Algorithm Hash digest
SHA256 cfc8e8ff1ca2a9458913cf1c94a000a7aea73258d5f1e5b2d20e74cf42c97082
MD5 401f9f06bf357d872bce2c30459207ed
BLAKE2b-256 97b74807d893ae43721ef13ef3ada416dfbec8c3797a8db9026ed4ee7d47ebc7

See more details on using hashes here.

File details

Details for the file pygans-2.0.3-py3-none-any.whl.

File metadata

  • Download URL: pygans-2.0.3-py3-none-any.whl
  • Upload date:
  • Size: 8.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.6.0.post20191030 requests-toolbelt/0.9.1 tqdm/4.40.0 CPython/3.7.5

File hashes

Hashes for pygans-2.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 2828f29460cf86def77b9dd0390d0bf7066e34116542e69262daba9385fd9037
MD5 fbd2c19a139f355640ca31279b796fd4
BLAKE2b-256 444514c0e442bdd57201c30ec46bfe7cc0a9e4d642ea2be09f381e9c6d24497f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page