DNN-mnist數據集識別

win10
python3.6
tensorflow1.12

import numpy as np
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/mnist/", one_hot=True)

# 超參設置
learning_rate = 0.01
num_steps = 500
batch_size = 128
display_step = 100

# 網絡參數
n_hidden_1 = 256
n_hidden_2 = 256
num_input = 784
num_classess = 10

# 輸入設置
X = tf.placeholder("float", [None, num_input])
Y = tf.placeholder("float", [None, num_classess])

# 網絡權重設置
weights = {
    "h1" : tf.Variable(tf.random_normal([num_input, n_hidden_1])),
    "h2" : tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    "out" : tf.Variable(tf.random_normal([n_hidden_2, num_classess]))
}
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([num_classess]))
}

# 定義NN網絡結構
def NN(x):
    layer_1 = tf.add(tf.matmul(x, weights["h1"]), biases["b1"])
    layer_2 = tf.add(tf.matmul(layer_1, weights["h2"]), biases["b2"])
    out = tf.matmul(layer_2, weights["out"]) + biases["out"]
    return out

# 初始化所定義的NN實例
logits = NN(X)

#定義誤差函數 與 優化方式
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)

# 定義檢驗模型效果的方式
correct_pred = tf.equal(tf.arg_max(logits, 1), tf.arg_max(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# 初始化變量
init = tf.global_variables_initializer()

# 將所有定義編譯成實際的 Tensorflow 圖模型並運行
with tf.Session() as sess:
    
    sess.run(init)
    
    for step in range(1, num_steps+1):
        batch_x, batch_y = mnist.train.next_batch(batch_size)
        # 進行前向傳播，後向傳播 以及優化
        sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})
        if step % display_step == 0 or step == 1:
            # 計算每一批數據的誤差及準確度
            loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x, Y: batch_y})
            print("Step " + str(step) + ", Minibatch Loss= " + 
                  "{:.4f}".format(loss) + ", Training Accuracy= "+ 
                  "{:.3f}".format(acc) )
            
    print("Optimization Finished!")
    
    # 測試集
    print("Testing Accuracy: ", sess.run(accuracy, feed_dict={X: mnist.test.images, Y: mnist.test.labels}))

執行結果：

Extracting /mnist/train-images-idx3-ubyte.gz
Extracting /mnist/train-labels-idx1-ubyte.gz
Extracting /mnist/t10k-images-idx3-ubyte.gz
Extracting /mnist/t10k-labels-idx1-ubyte.gz
WARNING:tensorflow:From :51: arg_max (from tensorflow.python.ops.gen_math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use argmax instead
Step 1, Minibatch Loss= 2579.7476, Training Accuracy= 0.203
Step 100, Minibatch Loss= 215.5095, Training Accuracy= 0.820
Step 200, Minibatch Loss= 111.4745, Training Accuracy= 0.883
Step 300, Minibatch Loss= 107.8162, Training Accuracy= 0.922
Step 400, Minibatch Loss= 154.5716, Training Accuracy= 0.797
Step 500, Minibatch Loss= 111.6394, Training Accuracy= 0.867
Optimization Finished!
Testing Accuracy: 0.8676