Skip to content

Instantly share code, notes, and snippets.

@e-lin
Last active July 9, 2019 12:17
Show Gist options
  • Save e-lin/8db8194e8be3a2fbcef1af354eee24c9 to your computer and use it in GitHub Desktop.
Save e-lin/8db8194e8be3a2fbcef1af354eee24c9 to your computer and use it in GitHub Desktop.
AutoEncoder: Training one Autoencoder at a time in multiple graphs
# image input
n_inputs = 28*28
# merged to one stacked AE
X = tf.placeholder(tf.float32, shape=[None, n_inputs])
hidden1 = tf.nn.elu(tf.matmul(X, W1) + b1)
hidden2 = tf.nn.elu(tf.matmul(hidden1, W2) + b2)
hidden3 = tf.nn.elu(tf.matmul(hidden2, W3) + b3)
outputs = tf.matmul(hidden3, W4) + b4
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment