def test_calculate_cls_vector(pooling, features, only_non_zero_vectors,
expected):
actual = DenseFeaturizer.aggregate_sequence_features(
features,
pooling_operation=pooling,
only_non_zero_vectors=only_non_zero_vectors)
assert np.all(actual == expected)
def get_default_config() -> Dict[Text, Any]:
"""The component's default config (see parent class for full docstring)."""
return {
**DenseFeaturizer.get_default_config(),
# Remote URL/Local path to model files
"model_url": None,
}
def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**DenseFeaturizer.get_default_config(),
# Specify what pooling operation should be used to calculate the vector of
# the complete utterance. Available options: 'mean' and 'max'
POOLING:
MEAN_POOLING,
}
def get_default_config() -> Dict[Text, Any]:
"""Returns LanguageModelFeaturizer's default config."""
return {
**DenseFeaturizer.get_default_config(),
# name of the language model to load.
"model_name": "bert",
# Pre-Trained weights to be loaded(string)
"model_weights": None,
# an optional path to a specific directory to download
# and cache the pre-trained model weights.
"cache_dir": None,
}
def get_default_config() -> Dict[Text, Any]:
"""Returns the component's default config."""
return {
**DenseFeaturizer.get_default_config(),
# specifies the language of the subword segmentation model
"lang": None,
# specifies the dimension of the subword embeddings
"dim": None,
# specifies the vocabulary size of the segmentation model
"vs": None,
# if set to True and the given vocabulary size can't be loaded for the given
# model, the closest size is chosen
"vs_fallback": True,
}