def predict(config,
concept,
positives,
vocab,
entity_model,
concept_model,
original_model,
val_data,
result=None):
entity_examples = examples_evaluation(config, concept, positives, vocab)
c_token_indices = [[
vocab.get(t.lower(), 1) for t in nltk.word_tokenize(neg)
] for neg in concept.names]
concept_examples = pad_sequences(c_token_indices,
padding='post',
maxlen=config.getint(
'embedding', 'length'))
entity_encodings = entity_model.predict_generator(entity_examples,
steps=len(positives))
concept_encodings = concept_model.predict(concept_examples)
###################
from sample import sped_up_format_x
convoluted_input = sped_up_format_x(entity_encodings, concept_encodings)
entity_encodings = Input(shape=(convoluted_input[0].shape[1], ),
dtype='float32',
name='entity_encodings')
concept_encodings = Input(shape=(convoluted_input[1].shape[1], ),
dtype='float32',
name='concept_encodings')
if sysargv5 == 'sem_matrix':
model = _predict_shared_encoder(original_model, entity_encodings,
concept_encodings)
elif sysargv5 == 'cosine_sim':
model = _predict_shared_encoder_dot(original_model, entity_encodings,
concept_encodings)
test_y = model.predict(convoluted_input)
if not result:
evaluation_parameter = callback.evaluate(val_data.mentions, test_y,
val_data.y)
else:
evaluation_parameter = evaluate_w_results(val_data.mentions, test_y,
val_data.y, concept, result)
return evaluation_parameter
def forward_pass_speedup_shared_encoder_dot_xDense(model,corpus_padded,concept_padded,pretrained):
'''
Model to speed up forward pass, used in callback for evaluation
'''
model_mention = _forward_pass_speedup_conv(model,['inp_mentions','embedding_layer','drop','conv1d','global_max_pooling1d_1'])
mentions = model_mention.predict(corpus_padded) # (787, 50)
model_candidate = _forward_pass_speedup_conv(model,['inp_candidates','embedding_layer','drop','conv1d','global_max_pooling1d_2'])
candidates = model_candidate.predict(concept_padded) # (67782,50)
logger.info('Formatting pooled mentions and candidates...')
# from sample import no_cangen_format_x
from sample import sped_up_format_x
convoluted_input = sped_up_format_x(mentions,candidates)
model_sem = _forward_pass_speedup_dot_xDense(model,convoluted_input)
return convoluted_input, model_sem
def predict(config, concept, positives, vocab, entity_model, concept_model, original_model,val_data,result=None):
entity_examples = examples_evaluation(config, concept, positives, vocab)
#entity_examples_1 = examples_(config, concept, positives, vocab, neg_count = 0)
#import pdb;pdb.set_trace()
c_token_indices = [[vocab.get(t.lower(), 1) for t in nltk.word_tokenize(neg)] for neg in concept.names]
concept_examples = pad_sequences(c_token_indices, padding='post', maxlen=config.getint('embedding','length'))
entity_encodings = entity_model.predict_generator(entity_examples, steps=len(positives))
concept_encodings = concept_model.predict(concept_examples)
###################
from sample import sped_up_format_x
convoluted_input = sped_up_format_x(entity_encodings,concept_encodings)
layerss = ['v_sem','hidden_layer','prediction_layer']
v_sem = original_model.get_layer(layerss[0])
d2 = original_model.get_layer(layerss[2])
if sysargv2 == 'full':
d1 = original_model.get_layer(layerss[1])
entity_encodings = Input(shape=(convoluted_input[0].shape[1],),dtype='float32', name='entity_encodings')
concept_encodings = Input(shape=(convoluted_input[1].shape[1],),dtype='float32', name='concept_encodings')
sem = cnn.semantic_similarity_layer(weights = v_sem.get_weights())([entity_encodings,concept_encodings])
if sysargv2 == 'full':
concatenate_list = [entity_encodings,concept_encodings,sem]
join_layer = Concatenate()(concatenate_list)
hidden_layer = Dense(d1.units, activation=d1.activation,weights=d1.get_weights())(join_layer)
prediction_layer = Dense(d2.units, activation=d2.activation,weights=d2.get_weights())(hidden_layer)
else:
prediction_layer = Dense(d2.units, activation=d2.activation,weights=d2.get_weights())(sem)
model = Model(inputs=[entity_encodings,concept_encodings], outputs=prediction_layer)
test_y = model.predict(convoluted_input)
if not result:
evaluation_parameter = callback.evaluate(val_data.mentions, test_y, val_data.y)
else:
evaluation_parameter = evaluate_w_results(val_data.mentions, test_y, val_data.y, concept, result)
return evaluation_parameter
def predict(config,
concept,
positives,
vocab,
entity_model,
concept_model,
original_model,
val_data,
result=None):
entity_examples = examples(config, concept, positives, vocab, neg_count=0)
c_token_indices = [[
vocab.get(t.lower(), 1) for t in nltk.word_tokenize(neg)
] for neg in concept.names]
concept_examples = pad_sequences(c_token_indices,
maxlen=config.getint(
'embedding', 'length'))
entity_encodings = entity_model.predict_generator(entity_examples,
steps=len(positives))
concept_encodings = concept_model.predict(concept_examples)
###################
from sample import sped_up_format_x
convoluted_input = sped_up_format_x(entity_encodings, concept_encodings)
layerss = ['v_sem', 'hidden_layer', 'prediction_layer']
v_sem = original_model.get_layer(layerss[0])
d1 = original_model.get_layer(layerss[1])
d2 = original_model.get_layer(layerss[2])
entity_encodings = Input(shape=(convoluted_input[0].shape[1], ),
dtype='float32',
name='entity_encodings')
concept_encodings = Input(shape=(convoluted_input[1].shape[1], ),
dtype='float32',
name='concept_encodings')
sem = cnn.semantic_similarity_layer(weights=v_sem.get_weights())(
[entity_encodings, concept_encodings])
#cos_sim = layers.dot([entity_encodings, concept_encodings], axes=-1, normalize=True, name='cos_sim')
concatenate_list = [entity_encodings, concept_encodings, sem]
join_layer = Concatenate()(concatenate_list)
hidden_layer = Dense(d1.units,
activation=d1.activation,
weights=d1.get_weights())(join_layer)
prediction_layer = Dense(d2.units,
activation=d2.activation,
weights=d2.get_weights())(hidden_layer)
model = Model(inputs=[entity_encodings, concept_encodings],
outputs=prediction_layer)
test_y = model.predict(convoluted_input)
if not result:
evaluation_parameter = callback.evaluate(val_data.mentions, test_y,
val_data.y)
else:
evaluation_parameter = evaluate_w_results(val_data.mentions, test_y,
val_data.y, concept, result)
###################
# sims = cosine_similarity(entity_encodings, concept_encodings)
# best_hits = np.argmax(sims, axis=-1)
# predictions = [concept.ids[i] for i in best_hits]
# return predictions
return evaluation_parameter
