import tensorflow as tf
from tensorflow.keras import datasets
from matplotlib import pyplot as plt
import os
import pysnooper
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# 自定义的预处理函数
def preprocess(x, y):
# 调用此函数时会自动传入x,y对象,shape为[b,28,28],[b]
# 标准化到0-1
x = tf.cast(x, dtype=tf.float32) / 255.
# 打平,-1代表不知道有多少图片
x = tf.reshape(x, [-1, 28 * 28])
# 转成整型张量
y = tf.cast(y, dtype=tf.int32)
# one-hot编码
y = tf.one_hot(y, depth=10)
# 返回的x,y将替换传入的x,y参数,从而实现数据的预处理功能
return x, y
# 加载MNIST数据集
(x, y), (x_test, y_test) = datasets.mnist.load_data()
# 构建Dataset对象
train_db = tf.data.Dataset.from_tensor_slices((x, y))
# 随机打散样本,不会打乱样本与标签映射关系
train_db = train_db.shuffle(1000)
# 设置批处理,batch size为128
train_db = train_db.batch(128)
# 预处理函数实现在preprocess中,传入参数名即可,.map()操作是将传入的两个字段做映射,分别传入函数、分别返回数值
train_db = train_db.map(preprocess)
# 设置重复次数为20次
train_db = train_db.repeat(20)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.shuffle(1000).batch(128).map(preprocess)
x, y = next(iter(train_db))
# print(train_db)
# print('train sample:', x.shape, y.shape)
# @pysnooper.snoop(watch='step')
def main():
lr = 1e-2
acce, 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]))
# 训练世代数
# 迭代数据集对象,带step参数
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
# loss
loss = tf.square(y-out)
# 均方误差
loss = tf.reduce_mean(loss)
grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
for p, q in zip([w1, b1, w2, b2, w3, b3], grads):
p.assign_sub(lr * q)
if step % 50 == 0:
print(step, 'loss:', float(loss))
losses.append(float(loss))
if step % 50 == 0:
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)
acce.append(total_correct / total)
plt.rcParams['font.sans-serif'] = ['SimHei'] # 显示中文标签
plt.rcParams['axes.unicode_minus'] = False
plt.figure()
x = [i * 80 for i in range(len(losses))]
plt.plot(x, losses, label='训练')
plt.ylabel('MSE')
plt.xlabel('Step')
plt.legend()
# plt.savefig('train.svg')
plt.show()
plt.figure()
plt.plot(x, acce, label='测试')
plt.ylabel('准确率')
plt.xlabel('Step')
plt.legend()
plt.show()
# plt.savefig('test.svg')
if __name__ == '__main__':
main()
python实现-Mnist数据集实战-注释超详细
最新推荐文章于 2023-10-13 18:27:56 发布