nlp_architect.models.np_semantic_segmentation.NpSemanticSegClassifier

class nlp_architect.models.np_semantic_segmentation.NpSemanticSegClassifier(num_epochs, callback_args, loss='binary_crossentropy', optimizer='adam', batch_size=128)[source]

NP Semantic Segmentation classifier model (based on tf.Keras framework).

Parameters
  • num_epochs (int) – number of epochs to train the model

  • **callback_args (dict) – callback args keyword arguments to init a Callback for the model

  • loss – the model’s cost function. Default is ‘tf.keras.losses.binary_crossentropy’ loss

  • optimizer (tf.keras.optimizers) – the model’s optimizer. Default is ‘adam’

__init__(num_epochs, callback_args, loss='binary_crossentropy', optimizer='adam', batch_size=128)[source]
Parameters
  • num_epochs (int) – number of epochs to train the model

  • callback_args (dict) – callback args keyword arguments to init Callback for the model

  • loss – the model’s loss function. Default is ‘tf.keras.losses.binary_crossentropy’ loss

  • optimizer (tf.keras.optimizers) – the model’s optimizer. Default is adam

  • batch_size (int) – batch size

Methods

__init__(num_epochs, callback_args[, loss, …])

param num_epochs

number of epochs to train the model

build(input_dim)

Build the model’s layers :param input_dim: the first layer’s input_dim :type input_dim: int

eval(test_set)

Evaluate the model’s test_set on error_rate, test_accuracy_rate and precision_recall_rate

fit(train_set)

Train and fit the model on the datasets

get_outputs(test_set)

Classify the dataset on the model

load(model_path)

Load pre-trained model’s .h5 file to NpSemanticSegClassifier object

save(model_path)

Save the model’s prm file in model_path location

build(input_dim)[source]

Build the model’s layers :param input_dim: the first layer’s input_dim :type input_dim: int

eval(test_set)[source]

Evaluate the model’s test_set on error_rate, test_accuracy_rate and precision_recall_rate

Parameters

test_set (numpy.ndarray) – The test set

Returns

loss, binary_accuracy, precision, recall and f1 measures

Return type

tuple(float)

fit(train_set)[source]

Train and fit the model on the datasets

Parameters
  • train_set (numpy.ndarray) – The train set

  • args – callback_args and epochs from ArgParser input

get_outputs(test_set)[source]

Classify the dataset on the model

Parameters

test_set (numpy.ndarray) – The test set

Returns

model’s predictions

Return type

list(numpy.ndarray)

load(model_path)[source]

Load pre-trained model’s .h5 file to NpSemanticSegClassifier object

Parameters

model_path (str) – local path for loading the model

save(model_path)[source]

Save the model’s prm file in model_path location

Parameters

model_path (str) – local path for saving the model