archieve: homework7
This commit is contained in:
@@ -0,0 +1,91 @@
|
||||
import numpy as np
|
||||
# 在文件开头添加兼容性设置
|
||||
import tensorflow.compat.v1 as tf
|
||||
tf.disable_v2_behavior()
|
||||
|
||||
# 加载MNIST数据集,通过设置 one_hot=True 来使用独热编码标签
|
||||
# 独热编码:对于每个图片的标签 y,10 位中仅有一位的值为 1,其余的为 0。
|
||||
mnist = tf.keras.datasets.mnist
|
||||
(x_train, y_train), (x_test, y_test) = mnist.load_data()
|
||||
|
||||
|
||||
# 权重正态分布初始化函数
|
||||
def weight_variable(shape):
|
||||
# 生成截断正态分布随机数,shape表示生成张量的维度,mean是均值(默认=0.0),stddev是标准差。
|
||||
# 取值范围为 [ mean - 2 * stddev, mean + 2 * stddev ],这里为[-0.2, 0.2]
|
||||
initial = tf.truncated_normal(shape, stddev=0.1)
|
||||
return tf.Variable(initial)
|
||||
|
||||
|
||||
# 偏置量初始化函数
|
||||
def bias_variable(shape):
|
||||
initial = tf.constant(0.1, shape=shape) # value=0.1, shape是张量的维度
|
||||
return tf.Variable(initial)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 预处理数据
|
||||
x_train = x_train.reshape(-1, 784).astype('float32') / 255.0
|
||||
x_test = x_test.reshape(-1, 784).astype('float32') / 255.0
|
||||
y_train = tf.keras.utils.to_categorical(y_train, 10)
|
||||
y_test = tf.keras.utils.to_categorical(y_test, 10)
|
||||
|
||||
# 替换原来的mnist变量使用方式
|
||||
mnist_dataset = (x_train, y_train), (x_test, y_test)
|
||||
|
||||
# 后续代码中所有mnist.train.xxx需要改为mnist_dataset[0][0]和mnist_dataset[0][1]
|
||||
# 所有mnist.test.xxx需要改为mnist_dataset[1][0]和mnist_dataset[1][1]
|
||||
print(x_train.shape[0]) # 输出训练集样本数 60000
|
||||
print(x_test.shape[0]) # 输出测试集样本数 10000
|
||||
|
||||
# 为训练数据集的输入 x 和标签 y 创建占位符
|
||||
x = tf.placeholder(tf.float32, [None, 784]) # 保持原样(已通过兼容性导入)
|
||||
y = tf.placeholder(tf.float32, [None, 10])
|
||||
keep_prob = tf.placeholder(tf.float32)
|
||||
|
||||
# 创建神经网络第1层,输入层,激活函数为relu
|
||||
W_layer1 = weight_variable([784, 500])
|
||||
b_layer1 = bias_variable([500])
|
||||
h1 = tf.add(tf.matmul(x, W_layer1), b_layer1) # W * x + b
|
||||
h1 = tf.nn.relu(h1)
|
||||
# 创建神经网络第2层,隐藏层,激活函数为relu
|
||||
W_layer2 = weight_variable([500, 1000])
|
||||
b_layer2 = bias_variable([1000])
|
||||
h2 = tf.add(tf.matmul(h1, W_layer2), b_layer2) # W * h1 + b,h1为第1层的输出
|
||||
h2 = tf.nn.relu(h2)
|
||||
# 创建神经网络第3层,隐藏层,激活函数为relu
|
||||
W_layer3 = weight_variable([1000, 300])
|
||||
b_layer3 = bias_variable([300])
|
||||
h3 = tf.add(tf.matmul(h2, W_layer3), b_layer3) # W * h2 + b,h2为第2层的输出
|
||||
h3 = tf.nn.relu(h3)
|
||||
# 创建神经网络第4层,输出层,激活函数为softmax
|
||||
W_layer4 = weight_variable([300, 10])
|
||||
b_layer4 = bias_variable([10])
|
||||
predict = tf.add(tf.matmul(h3, W_layer4), b_layer4) # W * h3 + b,h3为第3层的输出
|
||||
y_conv = tf.nn.softmax(tf.matmul(h3, W_layer4) + b_layer4)
|
||||
# 计算交叉熵代价函数
|
||||
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predict, labels=y))
|
||||
# 使用Adam下降算法优化交叉熵代价函数
|
||||
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
|
||||
# 预测是否准确的结果存放在一个布尔型的列表中
|
||||
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y, 1)) # argmax返回的矩阵行中的最大值的索引号
|
||||
# 求预测准确率
|
||||
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float')) # cast将布尔型的数据转换成float型的数据;reduce_mean求平均值
|
||||
|
||||
# 初始化
|
||||
init_op = tf.global_variables_initializer()
|
||||
|
||||
with tf.Session() as sess:
|
||||
sess.run(init_op)
|
||||
for i in range(550): # 训练样本为55000,分成550批,每批为100个样本
|
||||
# 手动实现next_batch
|
||||
batch_index = np.random.randint(0, x_train.shape[0], 100)
|
||||
batch = (x_train[batch_index], y_train[batch_index])
|
||||
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y: batch[1], keep_prob: 1.0})
|
||||
test_accuracy = accuracy.eval(feed_dict={x: x_test, y: y_test})
|
||||
print('step %d, training accuracy %g, test accuracy %g' % (i, train_accuracy, test_accuracy))
|
||||
# 每一步迭代,都会加载100个训练样本,然后执行一次train_step,并通过feed_dict,用训练数据替代x和y张量占位符。
|
||||
sess.run(train_step, feed_dict={x: batch[0], y: batch[1], keep_prob: 0.5})
|
||||
# 显示最终在测试集上的准确率
|
||||
print(
|
||||
'test accuracy %g' % accuracy.eval(feed_dict={x: x_test, y: y_test, keep_prob: 1.0}))
|
||||
Reference in New Issue
Block a user