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)
# plot part.
import matplotlib.pyplot as plt
import pandas as pd
pd.DataFrame(attention_vector,
columns=['attention (%)'
]).plot(kind='bar',
title='Attention Mechanism as '
'a function of input'
' dimensions.')
plt.show()
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)
# plot part.
import matplotlib.pyplot as plt
import pandas as pd
pd.DataFrame(attention_vector, columns=['attention (%)']).plot(kind='bar',
title='Attention Mechanism as '
'a function of input'
' dimensions.')
plt.show()
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)[1].flatten()
print('attention =', attention_vector)
# plot part.
import matplotlib.pyplot as plt
import pandas as pd
pd.DataFrame(attention_vector,
columns=['attention (%)'
]).plot(kind='bar',
title='Attention Mechanism as '
'a function of input'
' dimensions.')
plt.show()
if APPLY_ATTENTION_BEFORE_LSTM:
m = model_attention_applied_before_lstm()
else:
m = model_attention_applied_after_lstm()
m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
print(m.summary())
m.fit([inputs_1], outputs, epochs=1, batch_size=64, validation_split=0.1)
attention_vectors = []
for i in range(300):
testing_inputs_1, testing_outputs = get_data_recurrent(1, TIME_STEPS, INPUT_DIM)
attention_vector = np.mean(get_activations(m,
testing_inputs_1,
print_shape_only=True,
layer_name='attention_vec')[0], axis=2).squeeze()
print('attention =', attention_vector)
assert (np.sum(attention_vector) - 1.0) < 1e-5
attention_vectors.append(attention_vector)
attention_vector_final = np.mean(np.array(attention_vectors), axis=0)
# plot part.
import matplotlib.pyplot as plt
import pandas as pd
pd.DataFrame(attention_vector_final, columns=['attention (%)']).plot(kind='bar',
title='Attention Mechanism as '
'a function of input'
' dimensions.')
plt.show()
if APPLY_ATTENTION_BEFORE_LSTM:
m = model_attention_applied_before_lstm()
else:
m = model_attention_applied_after_lstm()
m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
print(m.summary())
m.fit([inputs_1], outputs, epochs=1, batch_size=64, validation_split=0.1)
attention_vectors = []
for i in range(300):
testing_inputs_1, testing_outputs = get_data_recurrent(1, TIME_STEPS, INPUT_DIM)
attention_vector = np.mean(get_activations(m,
testing_inputs_1,
print_shape_only=True,
layer_name='attention_vec')[0], axis=2).squeeze()
print('attention =', attention_vector)
assert (np.sum(attention_vector) - 1.0) < 1e-5
attention_vectors.append(attention_vector)
attention_vector_final = np.mean(np.array(attention_vectors), axis=0)
# plot part.
import matplotlib.pyplot as plt
import pandas as pd
pd.DataFrame(attention_vector_final, columns=['attention (%)']).plot(kind='bar',
title='Attention Mechanism as '
'a function of input'
' dimensions.')
plt.show()
labels=[0, 1, 2, 3, 4, 5, 6])
print('Epoch_{}:F1_{} ER_{}'.format(i, score_list['f1_overall_1sec'],
score_list['er_overall_1sec']))
print(conf_mat)
conf_mat = conf_mat / (utils.eps +
np.sum(conf_mat, 1)[:, None].astype('float'))
print(conf_mat)
model_path = '/data/users/21799506/Data/PRL2018/Evaluation/models_Temp/model_' + str(
i) + '.h5'
model.save(model_path)
plot_functions(nb_epoch, tr_loss, val_loss, f1_overall_1sec_list_eval,
er_overall_1sec_list_eval, f1_overall_1sec_list,
er_overall_1sec_list)
attention_vector = get_activations(model,
X_test,
print_shape_only=True,
layer_name='attention_vec')[0]
conv_vector = get_activations(model,
X_test,
print_shape_only=True,
layer_name='conv_vec')[0]
savevector = attention_vector.reshape(-1, 256, 256)
name = '/data/users/21799506/Data/PRL2018/Evaluation/AttentionVector_Temp/attention_vector' + str(
i)
sio.savemat(name, {'array_atten': savevector})
name = '/data/users/21799506/Data/PRL2018/Evaluation/AttentionVector_Temp/conv_vector' + str(
i)
sio.savemat(name, {'array_conv': conv_vector})
lossname = '/data/users/21799506/Data/PRL2018/Evaluation/models_Temp/performance'
sio.savemat(
metrics=['accuracy'])
print(m.summary())
plot_model(m, to_file='model_lstm.png', show_shapes=True)
m.fit([inputs_1], outputs, epochs=1, batch_size=64, validation_split=0.1)
attention_vectors = []
for i in range(50):
# 一つデータを生成する
x, y, attention_columns = get_data_recurrent(1, TIME_STEPS, INPUT_DIM,
5)
# attention_vec を指定して値を取り出している
test = get_activations(m,
x,
print_shape_only=True,
layer_name='attention_vec')
predicted = m.predict(x)
# print(len(test[0][0]))
# print(len(test[0][0][0]))
# print(np.mean(test[0], axis=2))
print("input", x.squeeze())
x_labels = [str(o) for o in x.squeeze()]
print(x_labels)
print("testing_outputs", y)
print("attention_columns", attention_columns)
# attention_vectorは、3番目の次元、例えば(1, 20, 32)なら 32 で平均を取ったもの。
plt.legend()
plt.show()
attention_vectors = []
for i in range(1):
testing_inputs_1, testing_inputs_2, testing_outputs = get_data_recurrent_1(
2, i + 1186, TIME_STEPS, INPUT_DIM, NN_FEATURES)
print("@@@@@@@@@@@@@@")
print(testing_inputs_1.shape)
testing_inputs_2 = testing_inputs_2.reshape(1, 13)
print(testing_inputs_2.shape)
print(testing_outputs.shape)
print("@@@@@@@@@@@@@@")
attention_vector = np.mean(get_activations(
m, [testing_inputs_1, testing_inputs_2],
print_shape_only=True,
layer_name='attention_vec')[0],
axis=2).squeeze()
# print('attention =', attention_vector)
# assert (np.sum(attention_vector) - 1.0) < 1e-5
attention_vectors.append(attention_vector)
attention_vector_final = np.mean(np.array(attention_vectors), axis=0)
# attention = [0.49647075 0.49483868 0.49929917 0.5051765 0.47675964 0.48862302
# 0.48885727 0.48410046 0.4866048 0.47961804]
# attention = [0.4820545 0.47170776 0.4883446 0.49935806 0.49587426 0.479177
# 0.4952951 0.47195023 0.49521935 0.51571256]
list_1 = []
