三种方法实现MNIST 手写数字识别

Posted 2020-10-30 夜雨最萌

MNIST数据集下载：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data 
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #one_hot 独热编码，也叫一位有效编码。在任意时候只有一位为1，其他位都是0

1 使用逻辑回归：

import tensorflow as tf

# 导入数据集
#from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# 变量
batch_size = 50

#训练的x(image),y(label)
# x = tf.Variable()
# y = tf.Variable()
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 模型权重
#[55000,784] * W = [55000,10]
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# 用softmax构建逻辑回归模型
pred = tf.nn.softmax(tf.matmul(x, W) + b)

# 损失函数(交叉熵)
cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), 1))

# 低度下降
optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cost)

# 初始化所有变量
init = tf.global_variables_initializer()

# 加载session图
with tf.Session() as sess:
    sess.run(init)

    # 开始训练
    for epoch in range(25):
        avg_cost = 0.
        
        total_batch = int(mnist.train.num_examples/batch_size)
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(optimizer, {x: batch_xs,y: batch_ys})
            #计算损失平均值
            avg_cost += sess.run(cost,{x: batch_xs,y: batch_ys}) / total_batch
        if (epoch+1) % 5 == 0:
            print("Epoch:", ‘%04d‘ % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("运行完成")

    # 测试求正确率
    correct = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
    print("正确率:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

结果：

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Epoch: 0005 cost= 0.394426425
Epoch: 0010 cost= 0.344705163
Epoch: 0015 cost= 0.323814137
Epoch: 0020 cost= 0.311426675
Epoch: 0025 cost= 0.302971779
运行完成
正确率: 0.9188

2 使用神经网络：

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


def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))


def model(X, w_h, w_o):
    h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions
    return tf.matmul(h, w_o) # note that we dont take the softmax at the end because our cost fn does that for us


mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

X = tf.placeholder("float", [None, 784])
Y = tf.placeholder("float", [None, 10])

w_h = init_weights([784, 625]) # create symbolic variables
w_o = init_weights([625, 10])

py_x = model(X, w_h, w_o)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # compute costs
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct an optimizer
predict_op = tf.argmax(py_x, 1)

# Launch the graph in a session
with tf.Session() as sess:
    # you need to initialize all variables
    tf.global_variables_initializer().run()

    for i in range(100):
        for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):
            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})
        print(i, np.mean(np.argmax(teY, axis=1) ==
                         sess.run(predict_op, feed_dict={X: teX})))

结果：

0 0.6898
1 0.8244
2 0.8635
3 0.881
4 0.8881
5 0.8931
6 0.8972
7 0.9005
8 0.9042
9 0.9062

3 使用卷积神经网络：

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

batch_size = 128
test_size = 256

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):
    l1a = tf.nn.relu(tf.nn.conv2d(X, w,                       # l1a shape=(?, 28, 28, 32)
                        strides=[1, 1, 1, 1], padding=‘SAME‘))
    l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],              # l1 shape=(?, 14, 14, 32)
                        strides=[1, 2, 2, 1], padding=‘SAME‘)
    l1 = tf.nn.dropout(l1, p_keep_conv)

    l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,                     # l2a shape=(?, 14, 14, 64)
                        strides=[1, 1, 1, 1], padding=‘SAME‘))
    l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],              # l2 shape=(?, 7, 7, 64)
                        strides=[1, 2, 2, 1], padding=‘SAME‘)
    l2 = tf.nn.dropout(l2, p_keep_conv)

    l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,                     # l3a shape=(?, 7, 7, 128)
                        strides=[1, 1, 1, 1], padding=‘SAME‘))
    l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],              # l3 shape=(?, 4, 4, 128)
                        strides=[1, 2, 2, 1], padding=‘SAME‘)
    l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])    # reshape to (?, 2048)
    l3 = tf.nn.dropout(l3, p_keep_conv)

    l4 = tf.nn.relu(tf.matmul(l3, w4))
    l4 = tf.nn.dropout(l4, p_keep_hidden)

    pyx = tf.matmul(l4, w_o)
    return pyx

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img
teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img


X = tf.placeholder("float", [None, 28, 28, 1])
Y = tf.placeholder("float", [None, 10])

w = init_weights([3, 3, 1, 32])       # 3x3x1 conv, 32 outputs
w2 = init_weights([3, 3, 32, 64])     # 3x3x32 conv, 64 outputs
w3 = init_weights([3, 3, 64, 128])    # 3x3x32 conv, 128 outputs
w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs
w_o = init_weights([625, 10])         # FC 625 inputs, 10 outputs (labels)

p_keep_conv = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

# Launch the graph in a session
with tf.Session() as sess:
    # you need to initialize all variables
    tf.global_variables_initializer().run()

    for i in range(10):
        training_batch = zip(range(0, len(trX), batch_size),
                             range(batch_size, len(trX)+1, batch_size))
        for start, end in training_batch:
            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
                                          p_keep_conv: 0.8, p_keep_hidden: 0.5})

        test_indices = np.arange(len(teX)) # Get A Test Batch
        np.random.shuffle(test_indices)
        test_indices = test_indices[0:test_size]

        print(i, np.mean(np.argmax(teY[test_indices], axis=1) ==
                         sess.run(predict_op, feed_dict={X: teX[test_indices],
                                                         Y: teY[test_indices],
                                                         p_keep_conv: 1.0,
                                                         p_keep_hidden: 1.0})))

结果：

0 0.9453125
1 0.9765625
2 0.9921875
3 0.98828125
4 0.984375
5 0.9921875
6 0.984375
7 0.9921875
8 0.98828125
9 0.99609375