vae.UnsupervisedModel¶
-
class
vae.
UnsupervisedModel
(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 unsupervised 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
Methods
collect_stats
(data, tensors[, enable_summaries])Collect statistics on the provided data evaluate
(data[, tensors, combine_func, …])Evaluate the model on the provided data. fit
(train_data[, validation_data, epochs, …])Train the model using the provided training data -
collect_stats
(data, tensors, enable_summaries=False, **feed_dict)¶ Collect statistics on the provided data
Parameters: - data
Input data. Can be a NumPy array, a SciPy sparse matrix, or a
Dataset
object.- tensors: list of str
List containing names of statistics to collect.
- enable_summaries : bool, optional (default=False)
Whether to write summaries to disk.
- **feed_dict
Additional keyword arguments to append to the feed dictionary used for evaluation.
Returns: - results : list
The collected statistics.
-
evaluate
(data, tensors=None, combine_func=<function _concat>, enable_summaries=False, batch_size=100, **feed_dict)¶ Evaluate the model on the provided data.
Parameters: - data
Input data. Can be a NumPy array, a SciPy sparse matrix, or a
Dataset
object.- tensors : list of str or None, optional (default=None)
List of tensor names to collect. Defaults to all available tensors.
- combine_func : optional
Function to use to combine collected data from all batches. If set to None, each batch is returned separately. Defaults to concatenation along the first axis.
- enable_summaries : bool, optional (default=False)
Whether to write summaries to disk.
- batch_size : int, optional (default=100)
Size of mini-batches.
- **feed_dict
Additional keyword arguments to append to the feed dictionary used for evaluation.
Yields: - results : list
If combine_func is None, a list containing outputs from a single batch, otherwise yields the combined results from all batches at once.
-
fit
(train_data, validation_data=None, epochs=1, shuffle=True, restore=False, summary_steps=None, init_feed_dict={}, validation_feed_dict={}, batch_size=100, **train_feed_dict)¶ Train the model using the provided training data
Parameters: - train_data
Training data. Can be a NumPy array, a SciPy sparse matrix, or a
Dataset
object.- validation_data : optional (default=None)
Validation data. Can be a NumPy array, a SciPy sparse matrix, or a
Dataset
object.- epochs : int (default=1)
Number of training epochs.
- shuffle : bool, optional (default=True)
Whether to shuffle training data before each epoch. Ignored if training data is a
Dataset
object.- restore : bool, optional (default=False)
Whether to restore the model from a previous checkpoint.
- summary_steps : int or None, optional (default=None)
Number of steps between writing summaries, or None for disabling summaries.
- init_feed_dict : dict, optional (default={})
Feed dictionary to append for initialization.
- validation_feed_dict : dict, optional (default={})
Feed dictionary to append for validation.
- batch_size : int, optional (default=100)
Size of mini-batches.
- **feed_dict
Additional keyword arguments to append to the feed dictionary used for training
Returns: - self
-
model_dir
¶ str: Directory for saving and restoring the model