vae.Model

class vae.Model(n_inputs, n_labels=None, optimizer='Adam', learning_rate=0.001, learning_rate_decay_fn=None, clip_gradients=None, model_dir=None, debug=False)

Base abstract class for models

Parameters:

n_inputs : int

Length of the input vector.

n_labels : int or None, optional (default=None)

Length of the label vector. If not provided, assumes data is un-labeled.

optimizer : str, optional (default=’Adam’)

Optimizer to use for training the model. See tf.contrib.layers.OPTIMIZER_CLS_NAMES for available options.

learning_rate : float, optional (default=0.001)

Learning rate for training the model.

learning_rate_decay_fn : optional (default=None)

Function for decaying the learning rate. Takes learning_rate and global_step, and returns the decayed learning rate.

clip_gradients : float or None, optional (default=None)

If provided, global clipping is applied to prevent the gradient norms from exceeding the provided value.

model_dir : str or None, optional (default=None)

Path to the model directory. Defaults to the current working directory.

debug : bool, optional (default=False):

Whether to open the TensorFlow session in debug mode.

Attributes:

model_dir

str: Directory for saving and restoring the model

model_dir

str: Directory for saving and restoring the model