b43325e297498269be86b281a02e2ef79664f273,train_variational_autoencoder_tensorflow.py,,inference_network,#,41

Before Change

    mu: Mean parameters for the variational family Normal
    sigma: Standard deviation parameters for the variational family Normal
  
  with slim.arg_scope([slim.fully_connected], activation_fn=tf.nn.relu):
    net = slim.flatten(x)
    net = slim.fully_connected(net, hidden_size)
    net = slim.fully_connected(net, hidden_size)

After Change

    mu: Mean parameters for the variational family Normal
    sigma: Standard deviation parameters for the variational family Normal
  
  inference_net = tfk.Sequential([
    tfkl.Flatten(),
    tfkl.Dense(hidden_size, activation=tf.nn.relu),
    tfkl.Dense(hidden_size, activation=tf.nn.relu),
    tfkl.Dense(latent_dim * 2, activation=None)
    ])
  gaussian_params = inference_net(x)
  // The mean parameter is unconstrained
  mu = gaussian_params[:, :latent_dim]

Instances