netplot 0.1.2

Ultralight 3D renderer of neural network architecture for TF/Keras Models

Netplot

A ultra-lightweight 3D renderer of the Tensorflow/Keras neural network architectures. This Library is working on Matplotlib visualization for now. In future the visualization can be moved to plotly for a more interactive visual of the neural network architecture.

Note: For now the rendering is working in Jupyter only Google Colab support is in works.

For more details visit NetPlot

Install with Pip

pip install netplot

Usage guide

from netplot import ModelPlot
import tensorflow as tf
import numpy as np

%matplotlib notebook

X_input = tf.keras.layers.Input(shape=(32,32,3))
X = tf.keras.layers.Conv2D(4, 3, activation='relu')(X_input)
X = tf.keras.layers.MaxPool2D(2,2)(X)
X = tf.keras.layers.Conv2D(16, 3, activation='relu')(X)
X = tf.keras.layers.MaxPool2D(2,2)(X)
X = tf.keras.layers.Conv2D(8, 3, activation='relu')(X)
X = tf.keras.layers.MaxPool2D(2,2)(X)
X = tf.keras.layers.Flatten()(X)
X = tf.keras.layers.Dense(10, activation='relu')(X)
X = tf.keras.layers.Dense(2, activation='softmax')(X)

model = tf.keras.models.Model(inputs=X_input, outputs=X)

modelplot = ModelPlot(model=model, grid=True, connection=True, linewidth=0.1)
modelplot.show()