Tensorflow（十五） —— Tensor数据加载实战

1. 解决tensorflow输出无关信息问题

import tensorflow as tf
import os 
from tensorflow.keras import datasets
from tensorflow import keras
# 解决tensorflow输出无关信息问题
os.environ['TF_CPP_MIN_LOG_LECEL'] = "2"
"""
2:表示只输出与报错相关的信息
0：输出一切信息
1：输出部分信息
"""

# 将GPU设置为memory_growth模式
gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
    tf.config.experimental.set_memory_growth(gpu, False)

2. 加载数据并转换类型

# 加载数据并转换类型
(x,y),(x_test,y_test) = datasets.mnist.load_data()
x = tf.convert_to_tensor(x,dtype = tf.float32).gpu()
y = tf.convert_to_tensor(y,dtype = tf.int32).gpu()
x_test = tf.convert_to_tensor(x_test,dtype=tf.float32).gpu()
y_test = tf.convert_to_tensor(y_test,dtype=tf.int32).gpu()
print("x:",x.shape,tf.reduce_min(x).numpy(),tf.reduce_max(x).numpy())
print("y:",y.shape,tf.reduce_min(y).numpy(),tf.reduce_max(y).numpy())

3. 数据分割成不同batch

# 数据分割成不同batch

# 先组合成为数据切片在切割成不同batch
train_db = tf.data.Dataset.from_tensor_slices((x,y)).shuffle(100000).batch(128) # 分成128个batch
test_db = tf.data.Dataset.from_tensor_slices((x_test,y_test)).shuffle(100000).batch(100)
# 查看数据集
train_iter = iter(train_db)
sample = next(train_iter)
print("sample:",sample[0].shape,sample[1].shape)

4. 定义权值和偏置为：Tensor类型的Variable

# 定义权值和偏置为：Tensor类型的Variable
"""
各层神经元数据流向[b,784] => [b,256] => [b,128] => [b,10]
"""
w1 = tf.Variable(tf.random.truncated_normal([784,256],stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))

w2 = tf.Variable(tf.random.truncated_normal([256,128],stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))

w3 = tf.Variable(tf.random.truncated_normal([128,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))

5. 参数训练

# 定义学习率
lr = tf.constant(1e-3)
# 训练每一层epoch
for epoch in range(10):
    # 训练 每一个batch
    for step,(x,y) in enumerate(train_db):

        # x特征归一化及像素点平铺化
        x = tf.reshape((x - tf.reduce_min(x))/(tf.reduce_max(x)-tf.reduce_min(x)),[-1,28*28])

        # 记录变量的梯度信息
        with tf.GradientTape() as tape:
            # 计算第一次输出h1
            h1 = tf.nn.relu(x@w1 + b1)

            #  计算第二层输出h2
            h2 = tf.nn.relu(h1@w2 + b2)

            # 计算第三层输出out
            out = h2@w3 + b3

            # 对y进行onehot编码
            y_onehot = tf.one_hot(y,depth = 10)

            # 计算损失函数
            loss = tf.reduce_mean(tf.square(out - y_onehot))

        # 计算梯度
        gradients = tape.gradient(loss,[w1,b1,w2,b2,w3,b3])

        # 权值更新
        w1.assign_sub(lr*gradients[0])
        b1.assign_sub(lr*gradients[1])
        w2.assign_sub(lr*gradients[2])
        b2.assign_sub(lr*gradients[3])
        w3.assign_sub(lr*gradients[4])
        b3.assign_sub(lr*gradients[5])
        
        
        # 测试集验证
        total_num,total_correct = 0,0
        for step1,(x,y) in enumerate(test_db):
            x = tf.reshape(x,[-1,28*28])
            h1 = tf.nn.relu(x@w1 + b1)
            h2 = tf.nn.relu(h1@w2 + b2)
            out = h2@w3 + b3
            
            prob = tf.nn.softmax(out,axis = 1)
            pred = tf.argmax(prob,axis = 1)
            
            correct = tf.cast(tf.equal(tf.cast(pred,dtype=tf.int32),y),dtype=tf.int32)
            correct = tf.reduce_sum(correct)
            
            total_num += y.shape[0]
            total_correct += correct
            
        acc = total_correct/total_num
        if step % 100 == 0:
            print(epoch,step,"ACC:",acc)

本文为参考龙龙老师的“深度学习与TensorFlow 2入门实战“课程书写的学习笔记

by CyrusMay 2022 04 16