利用Tensorflow實現神經網路模型

獵手家園發表於2017-05-09
神經網路模型

首先看一下神經網路模型，一個比較簡單的兩層神經。

程式碼如下：

# 定義引數
n_hidden_1 = 256    #第一層神經元
n_hidden_2 = 128    #第二層神經元
n_input = 784       #輸入大小，28*28的一個灰度圖，彩圖沒有什麼意義
n_classes = 10      #結果是要得到一個幾分類的任務

# 輸入和輸出
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
    
# 權重和偏置引數
stddev = 0.1
weights = {
    'w1': tf.Variable(tf.random_normal([n_input, 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")


def multilayer_perceptron(_X, _weights, _biases):
    #第1層神經網路 = tf.nn.啟用函式(tf.加上偏置量(tf.矩陣相乘(輸入Data, 權重W1), 偏置引數b1))
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['w1']), _biases['b1'])) 
    #第2層的格式與第1層一樣，第2層的輸入是第1層的輸出。
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, _weights['w2']), _biases['b2']))
    #返回預測值
    return (tf.matmul(layer_2, _weights['out']) + _biases['out'])
    
    
# 預測
pred = multilayer_perceptron(x, weights, biases)

# 計算損失函式和最佳化
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, 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"))

# 初始化
init = tf.global_variables_initializer()
print ("FUNCTIONS READY")


# 訓練
training_epochs = 20
batch_size      = 100
display_step    = 4
# LAUNCH THE GRAPH
sess = tf.Session()
sess.run(init)
# 最佳化器
for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = int(mnist.train.num_examples/batch_size)
    # 迭代訓練
    for i in range(total_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)
    avg_cost = avg_cost / total_batch
    # 列印結果
    if (epoch+1) % display_step == 0:
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        feeds = {x: batch_xs, y: batch_ys}
        train_acc = sess.run(accr, feed_dict=feeds)
        print ("TRAIN ACCURACY: %.3f" % (train_acc))
        feeds = {x: mnist.test.images, y: mnist.test.labels}
        test_acc = sess.run(accr, feed_dict=feeds)
        print ("TEST ACCURACY: %.3f" % (test_acc))
print ("OPTIMIZATION FINISHED")

 

相關文章