手写数字识别（使用tensorflow2.2.0框架）

手写数字识别（使用tensorflow2.2.0框架）
手写数字识别是最经典的分类实战

(1)首先导入我们需要用到的模块

import matplotlib
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets, layers, optimizers
#用下面二句代码可以去除警告
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

（2）加载MNIST数据集
下载下来的数据集被分成两部分：60000行的训练数据集（mnist.train）和10000行的测试数据集（mnist.test）。这样的切分很重要，在机器学习模型设计时必须有一个单独的测试数据集不用于训练而是用来评估这个模型的性能，从而更加容易把设计的模型推广到其他数据集上（泛化）。每一个MNIST数据单元有两部分组成：一张包含手写数字的图片x和一个对应的标签y(例如9的标签就是9)。

(x, y), (x_test, y_test) = datasets.mnist.load_data()
print('x:', x.shape, 'y:', y.shape, 'x test:', x_test.shape, 'y test:', y_test)

（3）预处理数据

def preprocess(x, y):
    # [b, 28, 28], [b]
    print(x.shape, y.shape)
    x = tf.cast(x, dtype=tf.float32) / 255.
    x = tf.reshape(x, [-1, 28 * 28])
    y = tf.cast(y, dtype=tf.int32)
    y = tf.one_hot(y, depth=10)
    return x, y

batchsz = 512
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000)
train_db = train_db.batch(batchsz)
train_db = train_db.map(preprocess)
train_db = train_db.repeat(20)
# %将数据切分为训练集合测试集%
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.shuffle(1000).batch(batchsz).map(preprocess)
x, y = next(iter(train_db))
print('train sample:', x.shape, y.shape)

（4）模型搭建和训练
模型的输入是28*28=728的图片
728(输入层)---->512(隐藏层第一层)----->256(隐藏层第二层)------->10（输出层对应0-9十个数字的分类）

def main():
    # learning rate
    lr = 1e-2
    accs, losses = [], []

    # 784 => 512
    w1, b1 = tf.Variable(tf.random.normal([784, 256], stddev=0.1)), tf.Variable(tf.zeros([256]))
    # 512 => 256
    w2, b2 = tf.Variable(tf.random.normal([256, 128], stddev=0.1)), tf.Variable(tf.zeros([128]))
    # 256 => 10
    w3, b3 = tf.Variable(tf.random.normal([128, 10], stddev=0.1)), tf.Variable(tf.zeros([10]))

    for step, (x, y) in enumerate(train_db):

        # [b, 28, 28] => [b, 784]
        x = tf.reshape(x, (-1, 784))

        with tf.GradientTape() as tape:
            # layer1.
            h1 = x @ w1 + b1
            h1 = tf.nn.relu(h1)
            # layer2
            h2 = h1 @ w2 + b2
            h2 = tf.nn.relu(h2)
            # output
            out = h2 @ w3 + b3
            # out = tf.nn.relu(out)
           
            # compute loss
            # [b, 10] - [b, 10]
            loss = tf.square(y - out)
            # [b, 10] => scalar
            loss = tf.reduce_mean(loss)

        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        for p, g in zip([w1, b1, w2, b2, w3, b3], grads):
            p.assign_sub(lr * g)

        # print
        if step % 80 == 0:
            print(step, 'loss:', float(loss))
            losses.append(float(loss))

        if step % 80 == 0:
            # evaluate/test
            total, total_correct = 0., 0

            for x, y in test_db:
                # layer1.
                h1 = x @ w1 + b1
                h1 = tf.nn.relu(h1)
                # layer2
                h2 = h1 @ w2 + b2
                h2 = tf.nn.relu(h2)
                # output
                out = h2 @ w3 + b3
                # [b, 10] => [b]
                pred = tf.argmax(out, axis=1)
                # convert one_hot y to number y
                y = tf.argmax(y, axis=1)
                # bool type
                correct = tf.equal(pred, y)
                # bool tensor => int tensor => numpy
                total_correct += tf.reduce_sum(tf.cast(correct, dtype=tf.int32)).numpy()
                total += x.shape[0]

            print(step, 'Evaluate Acc:', total_correct / total)

            accs.append(total_correct / total)

（5）训练结果展示：MSE和准确率

 plt.figure()
    x = [i * 80 for i in range(len(losses))]
    plt.plot(x, losses, color='C0', marker='s', label='训练')
    plt.ylabel('MSE')
    plt.xlabel('Step')
    plt.legend()
    plt.savefig('train.svg')
    plt.show()


    plt.figure()
    plt.plot(x, accs, color='C1', marker='s', label='测试')
    plt.ylabel('准确率')
    plt.xlabel('Step')
    plt.legend()
    plt.savefig('test.svg')
    plt.show()

if __name__ == '__main__':
    main()

（6）运行结果展示

本文地址：https://blog.csdn.net/wdxgj123/article/details/107065348