def test(model, data_test, label_test):
hit, miss = 0, 0
for i, sample in enumerate(data_test):
output = sample
for layer in model:
output = utils.run_layer(layer, output)
if np.argmax(output) == np.argmax(label_test[i]):
hit += 1
else:
miss += 1
print("ACERTOS: ", hit)
print("ERROS: ", miss)
print("TAXA DE ACERTOS: ", hit / (hit + miss) * 100)
def encoder_bloc(h, layer_spec, noise_std, update_BN, activation):
# Run the layer
z_pre = run_layer(h, layer_spec, output_name="z_pre")
# Compute mean and variance of z_pre (to be used in the decoder)
dim = len(z_pre.get_shape().as_list())
mean, var = tf.nn.moments(z_pre, axes=list(range(0, dim - 1)))
mean = tf.identity(mean, name="mean")
var = tf.identity(var, name="var")
# tf.identity在计算图内部创建了两个节点，send / recv节点，用来发送和接受两个变量，
# 如果两个变量在不同的设备上，比如 CPU 和 GPU，那么将会复制变量，如果在一个设备上，将会只是一个引用
# 返回一个和输入的 tensor 大小和数值都一样的 tensor ,类似于 y=x 操作
# Batch normalization
def training_batch_norm():
if update_BN:
z = update_batch_normalization(z_pre)
else:
z = batch_normalization(z_pre)
return z
def eval_batch_norm():
with tf.variable_scope("BN", reuse=tf.AUTO_REUSE):
mean = ewma.average(
tf.get_variable("running_mean", shape=z_pre.shape[-1]))
var = ewma.average(
tf.get_variable("running_var", shape=z_pre.shape[-1]))
z = batch_normalization(z_pre, mean, var)
return z
# Perform batch norm depending to the phase (training or testing)
z = tf.cond(training, training_batch_norm, eval_batch_norm)
z += tf.random_normal(tf.shape(z)) * noise_std
z = tf.identity(z, name="z")
# Center and scale plus activation
size = z.get_shape().as_list()[-1]
beta = tf.get_variable("beta", [size],
initializer=tf.constant_initializer(0))
gamma = tf.get_variable("gamma", [size],
initializer=tf.constant_initializer(1))
h = activation(z * gamma + beta)
return tf.identity(h, name="h")
def train(dataset):
global n_layers, learning_rate
model = utils.initialize_model(n_layers)
data_test, label_test, data_train, label_train = [], [], [], []
test_size = 0.1
epochs = 3
for i in range(len(dataset['data'])):
sample = utils.get_row(dataset, i)
if random.random() < test_size:
data_test.append(sample[0])
label_test.append(sample[1])
else:
data_train.append(sample[0])
label_train.append(sample[1])
for epoch in range(epochs):
for k in range(len(data_train)):
sample, label = data_train[k], label_train[k]
x_values, outputs = sample, []
outputs.append(x_values)
for layer in model:
x_values = utils.run_layer(layer, x_values)
outputs.append(x_values)
predicted = x_values
for i in range(len(model) - 1, -1, -1):
layer = model[i]
if i == len(model) - 1:
gradient = np.subtract(np.dot(
2, predicted), np.dot(
2, label)) * predicted * (1 - np.array(predicted))
else:
gradient = np.matmul(np.transpose(model[i + 1]['W']),
gradient) * outputs[i + 1] * (
1 - np.array(outputs[i + 1]))
layer = utils.update_layer(layer, gradient, learning_rate,
outputs[i] if i > 0 else sample)
test(model, data_test, label_test)
return model