Visualizing the architecture of your own model of Artificial Neural Networks
2 min readMay 7, 2018
This is a very simple post I’ve prepared just to help anyone who wants to visualize their artificial neural network architecture.
In this example, I will use a neural network built using Keras (http://keras.io/) and visualizing the architecture using ANN Visualizer (https://github.com/Prodicode/ann-visualizer).
The complete solution code can be found at:
You will need to install the following dependencies:
$ pip3 install keras
$ pip3 install ann_visualizer
$ pip install graphviz
$ pip install h5py
Now just train the template used the script:
# Create your first MLP in Keras
from keras.models import Sequential
from keras.layers import Dense
import numpy# fix random seed for reproducibility
numpy.random.seed(7)# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.data.csv", delimiter=",")# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]# create model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])# Fit the model
model.fit(X, Y, epochs=150, batch_size=10)# evaluate the model
scores = model.evaluate(X, Y)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))model_json = model.to_json()
with open("model.json", "w") as json_file:
json_file.write(model_json)# serialize weights to HDF5
model.save_weights("model.h5")
print("Saved model to disk")
Finally, you can view by invoking the ANN Visualizer from your saved template:
from ann_visualizer.visualize import ann_viz;
from keras.models import model_from_json
import numpy# fix random seed for reproducibility
numpy.random.seed(7)# load json and create model
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()model = model_from_json(loaded_model_json)# load weights into new model
model.load_weights("model.h5")ann_viz(model, title="Artificial Neural network - Model Visualization")
The result is a file (.pdf) that will be saved in the project directory.
References: