Keras Visualizer

A Python Library for Visualizing Keras Models.

Table of Contents

• Keras Visualizer
  • Table of Contents
  • Installation
    • Install
    • Upgrade
  • Usage
  • Parameters
  • Settings
  • Examples
    • Example 1
    • Example 2
    • Example 3
  • Supported layers

Installation

Install

Use python package manager (pip) to install Keras Visualizer.

pip install keras-visualizer

Upgrade

Use python package manager (pip) to upgrade Keras Visualizer.

pip install keras-visualizer --upgrade

Usage

from keras_visualizer import visualizer

# create your model here
# model = ...

visualizer(model, file_format='png')

Parameters

visualizer(model, file_name='graph', file_format=None, view=False, settings=None)

• model : a Keras model instance.
• file_name : where to save the visualization.
• file_format : file format to save 'pdf', 'png'.
• view : open file after process if True.
• settings : a dictionary of available settings.

Note :

• set file_format='png' or file_format='pdf' to save visualization file.
• use view=True to open visualization file.
• use settings to customize output image.

Settings

you can customize settings for your output image. here is the default settings dictionary:

settings = {
    # ALL LAYERS
    'MAX_NEURONS': 10,
    'ARROW_COLOR': '#707070',
    # INPUT LAYERS
    'INPUT_DENSE_COLOR': '#2ecc71',
    'INPUT_EMBEDDING_COLOR': 'black',
    'INPUT_EMBEDDING_FONT': 'white',
    'INPUT_GRAYSCALE_COLOR': 'black:white',
    'INPUT_GRAYSCALE_FONT': 'white',
    'INPUT_RGB_COLOR': '#e74c3c:#3498db',
    'INPUT_RGB_FONT': 'white',
    'INPUT_LAYER_COLOR': 'black',
    'INPUT_LAYER_FONT': 'white',
    # HIDDEN LAYERS
    'HIDDEN_DENSE_COLOR': '#3498db',
    'HIDDEN_CONV_COLOR': '#5faad0',
    'HIDDEN_CONV_FONT': 'black',
    'HIDDEN_POOLING_COLOR': '#8e44ad',
    'HIDDEN_POOLING_FONT': 'white',
    'HIDDEN_FLATTEN_COLOR': '#2c3e50',
    'HIDDEN_FLATTEN_FONT': 'white',
    'HIDDEN_DROPOUT_COLOR': '#f39c12',
    'HIDDEN_DROPOUT_FONT': 'black',
    'HIDDEN_ACTIVATION_COLOR': '#00b894',
    'HIDDEN_ACTIVATION_FONT': 'black',
    'HIDDEN_LAYER_COLOR': 'black',
    'HIDDEN_LAYER_FONT': 'white',
    # OUTPUT LAYER
    'OUTPUT_DENSE_COLOR': '#e74c3c',
    'OUTPUT_LAYER_COLOR': 'black',
    'OUTPUT_LAYER_FONT': 'white',
}

Note:

• set 'MAX_NEURONS': None to disable max neurons constraint.
• see list of color names here.

from keras_visualizer import visualizer

my_settings = {
    'MAX_NEURONS': None,
    'INPUT_DENSE_COLOR': 'teal',
    'HIDDEN_DENSE_COLOR': 'gray',
    'OUTPUT_DENSE_COLOR': 'crimson'
}

# model = ...

visualizer(model, file_format='png', settings=my_settings)

Examples

you can use simple examples as .py or .ipynb format in examples directory.

Example 1

from keras import models, layers
from keras_visualizer import visualizer

model = models.Sequential([
    layers.Dense(64, activation='relu', input_shape=(8,)),
    layers.Dense(6, activation='softmax'),
    layers.Dense(32),
    layers.Dense(9, activation='sigmoid')
])

visualizer(model, file_format='png', view=True)

---

Example 2

from keras import models, layers
from keras_visualizer import visualizer

model = models.Sequential()
model.add(layers.Conv2D(64, (3, 3), input_shape=(28, 28, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(3))
model.add(layers.Dropout(0.5))
model.add(layers.Activation('sigmoid'))
model.add(layers.Dense(1))

visualizer(model, file_format='png', view=True)

---

Example 3

from keras import models, layers
from keras_visualizer import visualizer

model = models.Sequential()
model.add(layers.Embedding(64, output_dim=256))
model.add(layers.LSTM(128))
model.add(layers.Dense(1, activation='sigmoid'))

visualizer(model, file_format='png', view=True)

Supported layers

Explore list of keras layers

1. Core layers

   • Input object
   • Dense layer
   • Activation layer
   • Embedding layer
   • Masking layer
   • Lambda layer

2. Convolution layers

   • Conv1D layer
   • Conv2D layer
   • Conv3D layer
   • SeparableConv1D layer
   • SeparableConv2D layer
   • DepthwiseConv2D layer
   • Conv1DTranspose layer
   • Conv2DTranspose layer
   • Conv3DTranspose layer

3. Pooling layers

   • MaxPooling1D layer
   • MaxPooling2D layer
   • MaxPooling3D layer
   • AveragePooling1D layer
   • AveragePooling2D layer
   • AveragePooling3D layer
   • GlobalMaxPooling1D layer
   • GlobalMaxPooling2D layer
   • GlobalMaxPooling3D layer
   • GlobalAveragePooling1D layer
   • GlobalAveragePooling2D layer
   • GlobalAveragePooling3D layer

4. Reshaping layers

   • Reshape layer
   • Flatten layer
   • RepeatVector layer
   • Permute layer
   • Cropping1D layer
   • Cropping2D layer
   • Cropping3D layer
   • UpSampling1D layer
   • UpSampling2D layer
   • UpSampling3D layer
   • ZeroPadding1D layer
   • ZeroPadding2D layer
   • ZeroPadding3D layer

5. Regularization layers

   • Dropout layer
   • SpatialDropout1D layer
   • SpatialDropout2D layer
   • SpatialDropout3D layer
   • GaussianDropout layer
   • GaussianNoise layer
   • ActivityRegularization layer
   • AlphaDropout layer