ab.util

Package helper utilities.

aboleth.util.batch(feed_dict, batch_size, n_iter=10000, N_=None)

Create random batches for Stochastic gradients.

Feed dict data generator for SGD that will yeild random batches for a a defined number of iterations, which can be infinite. This generator makes consecutive passes through the data, drawing without replacement on each pass.

Parameters:
  • feed_dict (dict of ndarrays) – The data with {tf.placeholder: data} entries. This assumes all items have the same length!
  • batch_size (int) – number of data points in each batch.
  • n_iter (int, optional) – The number of iterations
  • N (tf.placeholder (int), optional) – Place holder for the size of the dataset. This will be fed to an algorithm.
Yields:

dict – with each element an array length batch_size, i.e. a subset of data, and an element for N_. Use this as your feed-dict when evaluating a loss, training, etc.

aboleth.util.batch_prediction(feed_dict, batch_size)

Split the data in a feed_dict into contiguous batches for prediction.

Parameters:
  • feed_dict (dict of ndarrays) – The data with {tf.placeholder: data} entries. This assumes all items have the same length!
  • batch_size (int) – number of data points in each batch.
Yields:
  • ndarray – an array of shape approximately (batch_size,) of indices into the original data for the current batch
  • dict – with each element an array length batch_size, i.e. a subset of data. Use this as your feed-dict when evaluating a model, prediction, etc.

Note

The exact size of the batch may not be batch_size, but the nearest size that splits the size of the data most evenly.

aboleth.util.pos_variable(initial_value, name=None, **kwargs)

Make a tf.Variable that will remain positive.

Parameters:
  • initial_value (float, np.array, tf.Tensor) – the initial value of the Variable.
  • name (string) – the name to give the returned tensor.
  • kwargs (dict) – optional arguments to give the created tf.Variable.
Returns:

var – a tf.Variable within a Tensor that will remain positive through training.

Return type:

tf.Tensor

aboleth.util.summary_histogram(values)

Add a summary histogram to TensorBoard.

This will add a summary histogram with name variable.name.

Parameters:values (tf.Variable, tf.Tensor) – the Tensor to add to the summaries.
aboleth.util.summary_scalar(values)

Add a summary scalar to TensorBoard.

This will add a summary scalar with name variable.name.

Parameters:values (tf.Variable, tf.Tensor) – the Tensor to add to the summaries.