activation='softmax',
name='attention_vec')(inputs)
attention_mul = merge([inputs, attention_probs],
output_shape=32,
name='attention_mul',
mode='mul')
# ATTENTION PART FINISHES HERE,attention 输出映射
attention_mul = Dense(64)(attention_mul)
output = Dense(1, activation='sigmoid')(attention_mul)
model = Model(input=[inputs], output=output)
return model
if __name__ == '__main__':
N = 10000
inputs_1, outputs = get_data(N, input_dim)
m = build_model()
m.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
print(m.summary())
m.fit([inputs_1], outputs, epochs=20, batch_size=64, validation_split=0.5)
testing_inputs_1, testing_outputs = get_data(1, input_dim)
# Attention vector corresponds to the second matrix.
# The first one is the Inputs output.
attention_vector = get_activations(
m, testing_inputs_1, print_shape_only=True,
layer_name='attention_vec')[0].flatten()
print('attention =', attention_vector)
inputs = Input(shape=(input_dim,))
# ATTENTION PART STARTS HERE
attention_probs = Dense(input_dim, activation='softmax', name='attention_vec')(inputs)
attention_mul = merge([inputs, attention_probs], output_shape=32, name='attention_mul', mode='mul')
# ATTENTION PART FINISHES HERE
attention_mul = Dense(64)(attention_mul)
output = Dense(1, activation='sigmoid')(attention_mul)
model = Model(input=[inputs], output=output)
return model
if __name__ == '__main__':
N = 10000
inputs_1, outputs = get_data(N, input_dim)
m = build_model()
m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
print(m.summary())
m.fit([inputs_1], outputs, epochs=20, batch_size=64, validation_split=0.5)
testing_inputs_1, testing_outputs = get_data(1, input_dim)
# Attention vector corresponds to the second matrix.
# The first one is the Inputs output.
attention_vector = get_activations(m, testing_inputs_1,
print_shape_only=True,
layer_name='attention_vec')[0].flatten()
print('attention =', attention_vector)
