深度学习03——手写数字识别实例

1.利用Tensorflow自动加载mnist数据集

import tensorflow as tf

from tensorflow.keras import datasets, layers, optimizers

(xs,ys),_ = datasets.mnist.load_data()  # 自动下载mnist数据集
print('datasets:',xs.shape,ys.shape)

xs = tf.convert_to_tensor(xs,dtype=tf.float32)/255.  # 将mnist中的数据转为tensorflow格式
db = tf.data.Dataset.from_tensor_slices((xs,ys)) #将下载的数据存入datasets数据集

for step,(x,y) in enumerate(db):
    print(step,x.shape,y,y.shape)

2. 手写数字识别体验

2.1 准备网络结构与优化器

利用Sequential模块。

#准备网络结构与优化器
model = keras.Sequential([
    #3层结构
    layers.Dense(512, activation='relu'),
    layers.Dense(256, activation='relu'),
    layers.Dense(10)])

optimizer = optimizers.SGD(learning_rate=0.001)

2.2 计算损失函数与输出

        with tf.GradientTape() as tape:
            # [b, 28, 28] => [b, 784]
            x = tf.reshape(x, (-1, 28*28))
            # Step1. compute output
            # [b, 784] => [b, 10]
            out = model(x)
            # Step2. compute loss
            loss = tf.reduce_sum(tf.square(out - y)) / x.shape[0]

2.3 梯度计算与优化

        # Step3. optimize and update w1, w2, w3, b1, b2, b3
        grads = tape.gradient(loss, model.trainable_variables)
        # w' = w - lr * grad
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

2.4 循环

2.5 完整代码

import  os
import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import layers, optimizers, datasets

os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

#数据集的加载
(x, y), (x_val, y_val) = datasets.mnist.load_data() 
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
y = tf.one_hot(y, depth=10)
print(x.shape, y.shape)
train_dataset = tf.data.Dataset.from_tensor_slices((x, y))
train_dataset = train_dataset.batch(200)  #一次加载200张图片

#准备网络结构与优化器
model = keras.Sequential([
    #3层结构
    layers.Dense(512, activation='relu'),
    layers.Dense(256, activation='relu'),
    layers.Dense(10)])

optimizer = optimizers.SGD(learning_rate=0.001)

#计算迭代
def train_epoch(epoch):

    # Step4.loop
    for step, (x, y) in enumerate(train_dataset):

        with tf.GradientTape() as tape:
            # [b, 28, 28] => [b, 784]
            x = tf.reshape(x, (-1, 28*28))
            # Step1. compute output
            # [b, 784] => [b, 10]
            out = model(x)
            # Step2. compute loss
            loss = tf.reduce_sum(tf.square(out - y)) / x.shape[0]

        # Step3. optimize and update w1, w2, w3, b1, b2, b3
        grads = tape.gradient(loss, model.trainable_variables)
        # w' = w - lr * grad
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

        if step % 100 == 0:
            print(epoch, step, 'loss:', loss.numpy())

def train():
     #计算迭代30次
    for epoch in range(30):
        train_epoch(epoch)

if __name__ == '__main__':
    train()

（待完善。。。。）