（五）Tensorflow學習——神經網絡模型架構

以mnist數據集爲例，建立雙隱層神經網絡模型。

導入相關包

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

加載數據集

print('Download and Extract MNIST dataset')
mnist = input_data.read_data_sets('data/', one_hot=True)
print('MNIST loaded')

建立雙隱層神經網絡

雙隱層神經網絡：input_layer, layer_1, larer_2, output_layer

神經網絡模型架構

# NETWORK TOPOLOGIES
n_hidden_1 = 256  # 第一個隱藏層神經元
n_hidden_2 = 128  # 第二個隱藏層神經元
n_inupt = 784  # 輸入層神經元
n_classes = 10  # 輸出層神經元

# INPUTS AND OUTPUTS
x = tf.placeholder('float', [None, n_inupt])
y = tf.placeholder('float', [None, n_classes])

# NETWORK PARAMETERS，參數初始化
stddev = 0.1
weights = {
    'w1': tf.Variable(tf.random_normal([n_inupt, n_hidden_1], stddev=stddev)),
    'w2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], stddev=stddev)),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes], stddev=stddev)),
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes])),
}
print("NETWORK READY")

前向傳播

# 前向傳播
def multilayer_perceptron(_X, _weights, _biases):
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['w1']), _biases['b1']))
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, _weights['w2']), _biases['b2']))
    return (tf.matmul(layer_2, _weights['out']) + _biases['out'])

# 前向傳播 PREDICTION
pred = multilayer_perceptron(x, weights, biases)

反向傳播

# 反向傳播 COST AND OPTIMIZER
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optm = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(cost)
corr = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(corr, 'float'))

全局初始化

# INITIALZER
init = tf.global_variables_initializer()

模型訓練與預測

training_epochs = 100
batch_size = 100
display_step = 4

sess = tf.Session()
sess.run(init)

for epoch in range(training_epochs+1):
    avg_cost = 0.
    num_batch = int(mnist.train.num_examples/batch_size)
    for i in range(num_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        feeds = {x: batch_xs, y: batch_ys}
        sess.run(optm, feed_dict=feeds)
        avg_cost += sess.run(cost, feed_dict=feeds)/num_batch
    if epoch % display_step == 0:
        feeds_train = {x: batch_xs, y: batch_ys}
        feeds_test = {x: mnist.test.images, y: mnist.test.labels}
        train_acc = sess.run(accr, feed_dict=feeds_train)
        test_acc = sess.run(accr, feed_dict=feeds_test)
        print("Epoch: %03d/%03d cost: %.9f train_acc: %.3f test_acc: %.3f"
              % (epoch, training_epochs, avg_cost, train_acc, test_acc))
print('Done')

結果：