Deep Learning By Example

Model inputs

First off, we are going to define the model inputs function, which will create the model input placeholders to be used for feeding data to the computational model:

# defining the model inputsdef inputs(actual_dim, z_dim):    inputs_actual = tf.placeholder(tf.float32, (None, *actual_dim), name='input_actual')    inputs_latent_z = tf.placeholder(tf.float32, (None, z_dim), name='input_latent_z')    target = tf.placeholder(tf.int32, (None), name='target')    label_mask = tf.placeholder(tf.int32, (None), name='label_mask')    return inputs_actual, inputs_latent_z, target, label_mask