gpkg.keras.mnist

gpkg.keras.mnist contains MNIST models from Keras examples.

Name gpkg.keras.mnist
Description MNIST models in Keras (Guild AI)
Version 0.5.1
Source https://github.com/guildai/index/tree/master/gpkg/keras/mnist
Author Guild AI

acgan model

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

Operations

train

Train the model.
Flag Description Default
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

cnn model

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

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 128
epochs Number of epochs to train. 12

References

denoising-autoencoder model

Denoising autoencoder for MNIST in Keras.

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 128
epochs Number of epochs to train. 30

References

hierarchical-rnn model

Hierarchical RNN (HRNN) classifier for MNIST in Keras.

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 32
epochs Number of epochs to train. 5

References

irnn model

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

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 32
epochs Number of epochs to train. 200
learning‑rate Learning rate. 1e‑06

References

mlp model

Multilayer perceptron (MLP) classifier for MNIST in Keras.

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 128
epochs Number of epochs to train. 20

References

net2net model

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

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 32
epochs Number of epochs to train. 3

References

siamese model

Siamese MLP classifier for MNIST in Keras.

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 128
epochs Number of epochs to train. 20

References

swwae model

Stacked what-where autoencoder for MNIST in Keras.

Operations

train

Train the model.
Flag Description Default
batch‑size Training batch size. 128
epochs Number of epochs to train. 5
pool‑size kernel size used for the MaxPooling2D. 2

References