nlp_architect.contrib.tensorflow.python.keras.callbacks.ConllCallback

class nlp_architect.contrib.tensorflow.python.keras.callbacks.ConllCallback(x, y, y_vocab, batch_size=1)[source]

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

__init__(x, y, y_vocab, batch_size=1)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(x, y, y_vocab[, batch_size])

Initialize self.

on_batch_begin(batch[, logs])

on_batch_end(batch[, logs])

on_epoch_begin(epoch[, logs])

on_epoch_end(epoch[, logs])

on_train_batch_begin(batch[, logs])

on_train_batch_end(batch[, logs])

on_train_begin([logs])

on_train_end([logs])

set_model(model)

set_params(params)

on_batch_begin(batch, logs=None)
on_batch_end(batch, logs=None)
on_epoch_begin(epoch, logs=None)
on_epoch_end(epoch, logs=None)[source]
on_train_batch_begin(batch, logs=None)
on_train_batch_end(batch, logs=None)
on_train_begin(logs=None)
on_train_end(logs=None)
set_model(model)
set_params(params)