Last active
May 11, 2023 22:40
-
-
Save hageldave/45b6067b3bace90b03ed76abd0ff09e9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Autoencoder example for dimensionalilty reduction of MNIST | |
# Requires tensorflow and seaborn | |
# e.g.: pip install tensorflow-cpu seaborn | |
import tensorflow as tf | |
import numpy as np | |
import seaborn as sns | |
import matplotlib.pyplot as plt | |
def do_autoencoder_things(): | |
print("TensorFlow version:", tf.__version__) | |
# load the data set (mnist) | |
mnist = tf.keras.datasets.mnist | |
(x_train, y_train), (x_test, y_test) = mnist.load_data() | |
# normalize pixel values to range [0,1] | |
x_train, x_test = x_train / 255.0, x_test / 255.0 | |
# reshape the images to flat lines of pixels (from shape [n][28][28] to [n][28*28]) | |
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1] * x_train.shape[2]) | |
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1] * x_test.shape[2]) | |
# set up the layers of the network | |
# going from 28*28=784 to 128 to 32 to 8 to 2 dimensions | |
l1 = tf.keras.layers.Dense(128, activation='sigmoid') | |
l2 = tf.keras.layers.Dense(32, activation='sigmoid') | |
l3 = tf.keras.layers.Dense(8, activation='sigmoid') | |
l4 = tf.keras.layers.Dense(2, activation='sigmoid') | |
# now going from 2 dimensions up again | |
l5 = tf.keras.layers.Dense(8, activation='relu') | |
l6 = tf.keras.layers.Dense(32, activation='relu') | |
l7 = tf.keras.layers.Dense(128, activation='relu') | |
l8 = tf.keras.layers.Dense(x_train.shape[1], activation='relu') | |
# creating an encoder model from our layers | |
encoder = tf.keras.models.Sequential( | |
[l1,l2,l3,l4]) | |
# creating a combined encoder and decoder model from our layers | |
encoder_decoder = tf.keras.models.Sequential( | |
[l1,l2,l3,l4,l5,l6,l7,l8]) | |
# we will train the encoder_decoder model, therefore we compile it | |
encoder_decoder.compile(optimizer='adam', | |
loss=tf.keras.losses.MeanSquaredError(), | |
metrics=['mean_absolute_error']) | |
# check model performance before training | |
print(f'model evaluation: {encoder_decoder.evaluate(x_test, x_test, verbose=2)}') | |
# train the model, input and ground truth are the same because we optimize for best reconstruction | |
# (using x_test instead of x_train because it's smaller and training will be quicker) | |
encoder_decoder.fit(x_test, x_test, epochs=50) | |
# check perfromance after training | |
print(f'model evaluation: {encoder_decoder.evaluate(x_test, x_test, verbose=2)}') | |
# now that the weights in the layers are trained, we can use the encoder | |
reduced = encoder.predict(x_test) | |
# plot the resulting 2D points | |
sns.scatterplot(x=reduced[:, 0], y=reduced[:, 1], hue=y_test, palette="Paired") | |
plt.show() | |
def main(): | |
do_autoencoder_things() | |
if __name__ == '__main__': | |
main() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment