Metadata-Version: 2.1
Name: gpkg.keras.mnist
Version: 0.5.1
Summary: MNIST models in Keras (Guild AI)
Home-page: https://github.com/guildai/index/tree/master/gpkg/keras/mnist
Author: Guild AI
Author-email: packages@guild.ai
License: Apache 2.0
Keywords: gpkg
Platform: UNKNOWN
Requires-Dist: keras
Requires-Dist: matplotlib
Requires-Dist: Pillow

gpkg.keras.mnist
################

*MNIST models in Keras (Guild AI)*

Models
######

acgan
=====

*Auxiliary Classifier Generative Adversarial Network (ACGAN) for MNIST in
Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (100)*

**beta-1**
  *Beta 1 (0.5)*

**epochs**
  *Number of epochs to train (100)*

**learning-rate**
  *Learning rate (0.0002)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_acgan.py
- https://arxiv.org/abs/1511.06434

cnn
===

*Convolutional neural network (CNN) classifier for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (128)*

**epochs**
  *Number of epochs to train (12)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_cnn.py

denoising-autoencoder
=====================

*Denoising autoencoder for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (128)*

**epochs**
  *Number of epochs to train (30)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_denoising_autoencoder.py

hierarchical-rnn
================

*Hierarchical RNN (HRNN) classifier for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (32)*

**epochs**
  *Number of epochs to train (5)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_hierarchical_rnn.py
- https://arxiv.org/abs/1506.01057
- http://ieeexplore.ieee.org/document/7298714/

irnn
====

*Implementation of 'A Simple Way to Initialize Recurrent Networks of Rectified
Linear Units' with MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (32)*

**epochs**
  *Number of epochs to train (200)*

**learning-rate**
  *Learning rate (1e-06)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_irnn.py
- http://arxiv.org/pdf/1504.00941v2.pdf

mlp
===

*Multilayer perceptron (MLP) classifier for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (128)*

**epochs**
  *Number of epochs to train (20)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_mlp.py

net2net
=======

*Implementation of 'Net2Net: Accelerating Learning via Knowledge Transfer'
with MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (32)*

**epochs**
  *Number of epochs to train (3)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_net2net.py
- http://arxiv.org/abs/1511.05641

siamese
=======

*Siamese MLP classifier for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (128)*

**epochs**
  *Number of epochs to train (20)*

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_siamese.py
- http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf

swwae
=====

*Stacked what-where autoencoder for MNIST in Keras*

Operations
^^^^^^^^^^

train
-----

*Train the model*

Flags
`````

**batch-size**
  *Training batch size (128)*

**epochs**
  *Number of epochs to train (5)*

**pool-size**
  *kernel size used for the MaxPooling2D (2)

  Choices:
    2
    3

  *

References
^^^^^^^^^^

- https://github.com/keras-team/keras/blob/master/examples/mnist_swwae.py
- https://arxiv.org/abs/1311.2901v3
- https://arxiv.org/abs/1506.02351v8


