Stacked autoencoder in TensorFlow

The steps  to build a stacked autoencoder model in TensorFlow are as follows:

  1. First, define the hyper-parameters as follows:
learning_rate = 0.001n_epochs = 20batch_size = 100n_batches = int(mnist.train.num_examples/batch_size)
  1. Define the number of inputs (that is, features) and outputs (that is, targets). The number of outputs will be the same as the number of inputs:
# number of pixels in the MNIST image as number of inputsn_inputs = 784n_outputs = n_inputs
  1. Define the placeholders for input and output images:
x = tf.placeholder(dtype=tf.float32, name="x", shape=[None, n_inputs])y = tf.placeholder(dtype=tf.float32, name="y", shape=[None, n_outputs])
  1. Add the number of neurons for encoder and decoder ...

Get Mastering TensorFlow 1.x now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.