def __init__(self, nlp_toolkit: NLPToolkit):
self.nlp_toolkit = nlp_toolkit
archive_loader = ArchiveLoader(_MODEL_ARCHIVE)
config = archive_loader.get_config()
model_params = config.get('model')
vocabulary = archive_loader.get_vocabulary()
self.bidaf_model = BidirectionalAttentionFlow.from_params(
vocabulary, model_params)
model_state = archive_loader.get_model_state()
self.bidaf_model.load_state_dict(model_state)
self.vocab_reader = archive_loader.get_vocab_reader()
def setUp(self):
super(BidirectionalAttentionFlowTest, self).setUp()
constants.GLOVE_PATH = 'tests/fixtures/glove.6B.100d.sample.txt.gz'
reader_params = Params({
'token_indexers': {
'tokens': {
'type': 'single_id'
},
'token_characters': {
'type': 'characters'
}
}
})
dataset = SquadReader.from_params(reader_params).read(
'tests/fixtures/data/squad.json')
vocab = Vocabulary.from_dataset(dataset)
self.vocab = vocab
dataset.index_instances(vocab)
self.dataset = dataset
self.token_indexers = {
'tokens': SingleIdTokenIndexer(),
'token_characters': TokenCharactersIndexer()
}
self.model = BidirectionalAttentionFlow.from_params(
self.vocab, Params({}))
small_params = Params({
'text_field_embedder': {
'tokens': {
'type': 'embedding',
'pretrained_file': constants.GLOVE_PATH,
'trainable': False,
'projection_dim': 4
},
'token_characters': {
'type': 'character_encoding',
'embedding': {
'embedding_dim': 8
},
'encoder': {
'type': 'cnn',
'embedding_dim': 8,
'num_filters': 4,
'ngram_filter_sizes': [5]
}
}
},
'phrase_layer': {
'type': 'lstm',
'bidirectional': True,
'input_size': 8,
'hidden_size': 4,
'num_layers': 1,
},
'similarity_function': {
'type': 'linear',
'combination': 'x,y,x*y',
'tensor_1_dim': 8,
'tensor_2_dim': 8
},
'modeling_layer': {
'type': 'lstm',
'bidirectional': True,
'input_size': 32,
'hidden_size': 4,
'num_layers': 1,
},
'span_end_encoder': {
'type': 'lstm',
'bidirectional': True,
'input_size': 56,
'hidden_size': 4,
'num_layers': 1,
},
})
self.small_model = BidirectionalAttentionFlow.from_params(
self.vocab, small_params)
