def create_custom_objects(model_info):
custom_objects = {}
loss = model_info.get('loss')
if loss and loss['name'] == 'weighted_categorical_crossentropy':
loss_f = helper.weighted_categorical_crossentropy(
np.array(loss['weights']))
custom_objects['loss'] = loss_f
if loss and loss['name'] == 'crf':
custom_objects['CRF'] = CRF
custom_objects['crf_loss'] = crf_loss
custom_objects['crf_viterbi_accuracy'] = CRF(128).accuracy
return custom_objects
def create_custom_objects(model_info):
custom_objects = {}
loss = model_info.get('loss')
if loss and loss['name'] == 'weighted_categorical_crossentropy':
loss_f = helper.weighted_categorical_crossentropy(
np.array(loss['weights']))
custom_objects['loss'] = loss_f
if loss and loss['name'] == 'crf':
custom_objects['CRF'] = CRF
custom_objects['crf_loss'] = crf_loss
custom_objects['crf_viterbi_accuracy'] = CRF(128).accuracy
embedding = model_info.get('embedding')
if embedding and embedding['type'] == 'bert':
custom_objects['NonMaskingLayer'] = helper.NonMaskingLayer
custom_objects.update(get_bert_custom_objects())
return custom_objects
def create_custom_objects(model_info):
custom_objects = {}
loss = model_info.get('model_info', {}).get('loss')
if loss and loss['name'] == 'weighted_categorical_crossentropy':
loss_f = helper.weighted_categorical_crossentropy(np.array(loss['weights']))
custom_objects['loss'] = loss_f
architect_name = model_info.get('architect_name')
if architect_name and 'CRF' in architect_name:
custom_objects['CRF'] = CRF
custom_objects['crf_loss'] = crf_loss
custom_objects['crf_accuracy'] = crf_accuracy
embedding = model_info.get('embedding')
if embedding and embedding['embedding_type'] == 'bert':
custom_objects['NonMaskingLayer'] = helper.NonMaskingLayer
custom_objects.update(get_bert_custom_objects())
custom_objects['AttentionWeightedAverage'] = AttentionWeightedAverage
custom_objects['KMaxPooling'] = KMaxPooling
return custom_objects
def build_model(
self,
x_train: List[List[str]],
y_train: List[List[str]],
x_validate: List[List[str]] = None,
y_validate: List[List[str]] = None,
labels_weight: bool = None,
default_labels_weight: float = 50.0,
):
assert len(x_train) == len(y_train)
self.build_token2id_label2id_dict(x_train, y_train, x_validate,
y_validate)
if not self.model:
if self.embedding.sequence_length == 0:
self.embedding.sequence_length = sorted(
[len(x) for x in x_train])[int(0.95 * len(x_train))]
logging.info('sequence length set to {}'.format(
self.embedding.sequence_length))
if labels_weight:
weights = []
initial_weights = {k.PAD: 1, k.BOS: 1, k.EOS: 1, 'O': 1}
for label in self.label2idx.keys():
weights.append(
initial_weights.get(label, default_labels_weight))
loss_f = helper.weighted_categorical_crossentropy(
np.array(weights))
self.model_info['loss'] = {
'func': 'weighted_categorical_crossentropy',
'weights': weights
}
self._prepare_model()
self._compile_model()
self.model.summary()
def fit(self,
x_train: List[List[str]],
y_train: List[List[str]],
x_validate: List[List[str]] = None,
y_validate: List[List[str]] = None,
batch_size: int = 64,
epochs: int = 5,
labels_weight: bool = None,
default_labels_weight: float = 50.0,
fit_kwargs: Dict = None,
**kwargs):
"""
:param x_train: list of training data.
:param y_train: list of training target label data.
:param batch_size: batch size for trainer model
:param epochs: Number of epochs to train the model.
:param x_validate: list of validation data.
:param y_validate: list of validation target label data.
:param y_validate: list of validation target label data.
:param y_validate: list of validation target label data.
:param labels_weight: set class weights for imbalanced classes
:param default_labels_weight: default weight for labels not in labels_weight dict
:param fit_kwargs: additional kwargs to be passed to
:func:`~keras.models.Model.fit`
:return:
"""
assert len(x_train) == len(y_train)
self.build_token2id_label2id_dict(x_train, y_train, x_validate,
y_validate)
if len(x_train) < batch_size:
batch_size = len(x_train) // 2
if not self.model:
if self.embedding.sequence_length == 0:
self.embedding.sequence_length = sorted(
[len(x) for x in x_train])[int(0.95 * len(x_train))]
logging.info('sequence length set to {}'.format(
self.embedding.sequence_length))
if labels_weight:
weights = []
initial_weights = {k.PAD: 1, k.BOS: 1, k.EOS: 1, 'O': 1}
for label in self.label2idx.keys():
weights.append(
initial_weights.get(label, default_labels_weight))
loss_f = helper.weighted_categorical_crossentropy(
np.array(weights))
self.model_info['loss'] = {
'func': 'weighted_categorical_crossentropy',
'weights': weights
}
self.build_model(loss_f=loss_f,
metrics=['categorical_accuracy', 'acc'])
else:
self.build_model()
train_generator = self.get_data_generator(x_train, y_train, batch_size)
if fit_kwargs is None:
fit_kwargs = {}
if x_validate:
validation_generator = self.get_data_generator(
x_validate, y_validate, batch_size)
fit_kwargs['validation_data'] = validation_generator
fit_kwargs['validation_steps'] = len(x_validate) // batch_size
self.model.fit_generator(train_generator,
steps_per_epoch=len(x_train) // batch_size,
epochs=epochs,
**fit_kwargs)