nlp_architect.nn.tensorflow.python.keras package

Subpackages

• nlp_architect.nn.tensorflow.python.keras.layers package
  • Submodules
  • nlp_architect.nn.tensorflow.python.keras.layers.crf module
  • Module contents
• nlp_architect.nn.tensorflow.python.keras.utils package
  • Submodules
  • nlp_architect.nn.tensorflow.python.keras.utils.layer_utils module
  • Module contents

Submodules

nlp_architect.nn.tensorflow.python.keras.callbacks module

class nlp_architect.nn.tensorflow.python.keras.callbacks.ConllCallback(x, y, y_vocab, batch_size=1)

Bases: tensorflow.python.keras.callbacks.Callback

A Tensorflow(Keras) Conlleval evaluator. Runs the conlleval script for given x and y inputs. Prints Conlleval F1 score on the end of each epoch.

Parameters:

• x – features matrix
• y – labels matrix
• y_vocab (dict) – int-to-str labels lexicon
• batch_size (int, optional) – batch size

on_epoch_end(epoch, logs=None)

Called at the end of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Parameters:

• epoch – integer, index of epoch.
• logs – dict, metric results for this training epoch, and for the validation epoch if validation is performed. Validation result keys are prefixed with val_.

Module contents