【Tensorflow2.x学习笔记】day04

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets

# 去除警告
import os

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

# 导入数据集
# x:[60k,28,28]
# y:[60k]
(x, y), _ = datasets.mnist.load_data()

# 转换为tensorflow类型
# x:[0,255]==>[0,1.]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)

# 查看最小值最大值
print(x.shape, y.shape, x.dtype, y.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))

# 创建batch,128
train_db = tf.data.Dataset.from_tensor_slices((x, y)).batch(128)
train_iter = iter(train_db)
sample = next(train_iter)
print("batch:", sample[0].shape, sample[1].shape)

# [b,784]=>[b,256]=>[b,128]=>[b,10]
# [dim_in,dim_out],[dim_out]
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]))

lr = 1e-3
for eporch in range(10):#对整个数据集进行迭代
    for step, (x, y) in enumerate(train_db):#对batch进行迭代
        # x:[128,28,28]=>[b,28*28]
        # y:[128]

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

        with tf.GradientTape() as tape:
            # x : [b , 28*28 ]
            # h1 = x@w1 +b1

            # [b,784]@[784,256]+[256]=>[b,256]+[256]=>[b,256]+[b,256]
            h1 = x @ w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            h1 = tf.nn.relu(h1)
            # [b,256]=>[b,128]
            h2 = h1 @ w2 + b2
            h2 = tf.nn.relu(h2)
            # [b,128]=>[b,10]
            out = h2 @ w3 + b3

            # 计算误差loss
            # out : [b, 10]
            # y:[b]=>[b,10]
            y_onehot = tf.one_hot(y, depth=10)

            # MSE
            # [b,10]
            loss = tf.square(y_onehot - out)
            # mean:scalar
            loss = tf.reduce_mean(loss)

        # 计算梯度
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # wl = wl - lr *wl_grad
        w1.assign_sub(lr*grads[0])
        b1.assign_sub(lr*grads[1])
        w2.assign_sub(lr*grads[2])
        b2.assign_sub(lr*grads[3])
        w3.assign_sub(lr*grads[4])
        b3.assign_sub(lr*grads[5])

        if step % 100 == 0:
            print(eporch,step, 'loss:', float(loss))

concat实现张量的合并要求最多有一个维度不同

stack要求所有维度数都要一样

unstack固定的将指定维度全部打散，成为列表形式

可以随意指定分割

2-范数

1-范数