def test_attention_mv2(batch_size, word_embed_size, sent_embed_size,
doc_embed_size, vocab_size, max_words, max_sents,
num_classes, should_fit_model):
""" AttentionMV: full """
# sentence encoder
E = np.random.random((vocab_size, word_embed_size))
sent_inputs = Input(shape=(max_words, ), dtype="int32")
sent_emb = Embedding(input_dim=vocab_size,
output_dim=word_embed_size,
weights=[E])(sent_inputs)
sent_enc = Bidirectional(GRU(sent_embed_size,
return_sequences=True))(sent_emb)
sent_vec = GlobalAveragePooling1D()(sent_enc)
sent_att = custom_attn.AttentionMV()([sent_enc, sent_vec])
sent_model = Model(inputs=sent_inputs, outputs=sent_att)
# sent_enc = Bidirectional(GRU(sent_embed_size,
# return_sequences=False))(sent_emb)
# sent_model = Model(inputs=sent_inputs, outputs=sent_enc)
# document pipeline
doc_inputs = Input(shape=(max_sents, max_words), dtype="int32")
doc_emb = TimeDistributed(sent_model)(doc_inputs)
doc_enc = Bidirectional(GRU(doc_embed_size,
return_sequences=True))(doc_emb)
doc_vec = GlobalAveragePooling1D()(doc_enc)
doc_att = custom_attn.AttentionMV()([doc_enc, doc_vec])
fc1_dropout = Dropout(0.2)(doc_att)
fc1 = Dense(50, activation="relu")(fc1_dropout)
fc2_dropout = Dropout(0.2)(fc1)
doc_pred = Dense(num_classes, activation="softmax")(fc2_dropout)
model = Model(inputs=doc_inputs, outputs=doc_pred)
model.summary()
if should_fit_model:
X = np.random.random((batch_size * 2, max_sents, max_words))
y = np.random.randint(0, num_classes, batch_size * 2)
Y = np_utils.to_categorical(y, num_classes=num_classes)
model.compile(optimizer="adam", loss="categorical_crossentropy")
model.fit(X, Y, batch_size=batch_size, epochs=1)
return
def test_attention_mv1(batch_size, word_embed_size, sent_embed_size,
num_classes, max_words, vocab_size, should_fit_model):
""" AttentionMV: sentence only """
E = np.random.random((vocab_size, word_embed_size))
sent_inputs = Input(shape=(max_words, ), dtype="int32")
sent_emb = Embedding(input_dim=vocab_size,
output_dim=word_embed_size,
weights=[E])(sent_inputs)
sent_enc = Bidirectional(GRU(sent_embed_size,
return_sequences=True))(sent_emb)
# generate summary vector
sent_vec = GlobalAveragePooling1D()(sent_enc)
sent_att = custom_attn.AttentionMV()([sent_enc, sent_vec])
fc1_dropout = Dropout(0.2)(sent_att)
fc1 = Dense(50, activation="relu")(fc1_dropout)
fc2_dropout = Dropout(0.2)(fc1)
sent_pred = Dense(num_classes, activation="softmax")(fc2_dropout)
model = Model(inputs=sent_inputs, outputs=sent_pred)
model.summary()
if should_fit_model:
X = np.random.random((batch_size * 2, max_words))
y = np.random.randint(0, num_classes, batch_size * 2)
Y = np_utils.to_categorical(y, num_classes=num_classes)
model.compile(optimizer="adam", loss="categorical_crossentropy")
model.fit(X, Y, batch_size=batch_size, epochs=1)
return