keras-visualizer 2.4

A Keras Model Visualizer

Keras Visualizer

A Python Library for Visualizing Keras Models.

Keras Visualizer on GitHub
Keras Visualizer on PyPI
Keras Visualizer on Libraries.io

Dependencies

• keras
• graphviz

sudo pip3 install keras
sudo apt-get install graphviz && pip3 install graphviz

Installation

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

pip3 install keras-visualizer

Usage

import

from keras_visualizer import visualizer

function

visualizer(model) # save model
visualizer(model, format='png') # save both model & image file for visualizing model
visualizer(model, format='png', view=True) # open image file after visualization

Documentation

visualizer(model, filename='graph', format=None, view=False)

• model : a Keras model instance.
• filename : where to save the visualization.
• format : file format to save 'pdf', 'png'.
• view : open file after process if True.

Note : change format='png' or format='pdf' to save visualization file. use view=True to open visualization file.

Example

you can use simple examples 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, format='png', view=True)

---

Example 2 :

from keras import models  
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Activation  
from keras_visualizer import visualizer  

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

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