TensorFlow入门2

TensorFlow的基本操作

• 向前传播（张量）–实战

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

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

(x, y), (test_x, test_y) = datasets.mnist.load_data()

x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
print(x.shape, tf.reduce_max(x), tf.reduce_min(x))
print(y.shape, tf.reduce_max(y), tf.reduce_min(y))

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

# [b, 784] -> [b, 256] -> [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]))

lr = 1e-3

for epoch in range(10):
    # h1 = x@w1 + b1
    for step, (x, y) in enumerate(train_db):
        x = tf.reshape(x, [-1, 28*28])

        with tf.GradientTape() as tape:
            # 784->256
            h1 = x@w1 + b1
            h1 = tf.nn.relu(h1)
            # 256->128
            h2 = h1@w2 + b2
            h2 = tf.nn.relu(h2)
            # 128->10
            out = h2@w3 + b3

            # compute loss
            # out = [b, 10]
            # y[b] -> y[b,10]
            y_onehot = tf.one_hot(y, depth=10)
            loss = tf.square(y_onehot - out)
            loss = tf.reduce_mean(loss)  # 这个是求均值

        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # w1 = w1 - lr*w1_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("step:", step, "loss = ", loss)

• Tensor拼接

  # tf.concat([tensor1, tensor2], axis=x)
  a = tf.fill([2,3,4], 5)
  b = tf.fill([3,3,4], 6)
  c = tf.concat([a, b], axis=0)  # c.shape=[5,3,4]
  
  # tf.stack([tensor1,tensor2],axis=x) 与tf.concat的区别在于，stack会创建新的维度
  d = tf.fill([2,3,4], 5)
  e = tf.fill([2,3,4], 6)
  f = tf.stack([d, e], axis=0)  # f.shape = [2,2,3,4]
  dd, ee = tf.unstack(f,axis=0)  # 拆分，拆分之后dd和ee与d，e一样
  
  # tf.split(tensor, axis=x, num_or_size_splits=xxx) xxx为数字，就是均分，为列表就是分割大小
  g = tf.fill([4,8,10], 10)
  h = tf.split(g,axis=0,num_or_size_splits=2)  # h包含两个[2,8,10]
  i = tf.split(g,axis=0,num_or_size_splits=[1,1,2])  # i包含三个
  

• 数据统计

  # 向量的范数
  # tf.norm(tensor， ord = x, axis = xx)  ->x=1(一范数) x=2(二范数)
  # 一范数：所有元素绝对值之和
  # 二范数：所有元素平方和开根号
  # 默认是二范数
  a = tf.ones([2,2])
  tf.norm(a)  # 为2
  tf.norm(a, ord = 1, axis = 0)  # [2., 2.]
  
  # tf.reduce_min/max/mean(tensor, axis=xxx)
  # 不给定axis，默认全部
  
  # tf.argmax(tensor, axis=xxx) 不指定选第一个
  # tf.argmin(tensor, axis=xxx)
  b = tf.random.normal([4,10])
  d = tf.argmax(b)  # d.shape = [1, 10]
  
  # tf.equal(tensor1, tensor2) ->return [True, False, ...]
  e = tf.range(5)  # [0,1,2,3,4]
  f = tf.constant([1,2,3,4,5])
  g = tf.equal(e.f)  # g = [False, False, False, False, False]
  
  # tf.unique(a)  去重
  

• 张量排序

  # tf.sort(tensor, direction='DESCENDING')  按元素降序
  # tf.argsort(tensor, direction = 'DESCENDING') 降序的索引
  
  # tf.math.top_k(tensor, k) ->返回一个tuple
  # tuple.indices ->返回top k的索引
  # tuple.values  ->返回top k的数值
  a = tf.constant([[1, 2, 3], [4, 5, 6], [4, 5, 7], [7, 8, 9]])
  b = tf.math.top_k(a, 2)
  print(b.indices)
  print(b.values)
  

• 填充与复制

  # 扩张tf.pad(tensor, [[上下],[左右]])
  a = tf.reshape(tf.range(9), [3,3])
  b = tf.pad(a, [[1,0], [0,0]])  # 上面加一行
  
  # tf.tile(tensor, [xxx])  xxx:代表哪个维度扩大几倍
  c = tf.constant([[0,1,2], [3,4,5], [6,7,8]])
  d = tf.tile(c, [1,2])  # d.shape=[3,6]
  d -> [[0, 1, 2, 0, 1, 2], [3, 4, 5, 3, 4, 5], [6, 7, 8, 6, 7, 8]]
  

• 张量限幅

  # tf.maximum(tensor, xx) : 所有都大于xx
  # tf,minimum(tensor, xx) : 所有都小于xx
  # tf.clip_by_value(tensor, xx, xxx) : 所有都在xx - xxx之间
  # tf.nn.relu(a) : relu函数其实就是使用tf.maximum(tensor, 0)
  # tf.clip_by_norm(tensor, 15) : 把tensor的二范数限制在15左右，做一个放缩。只改变模，不改变方向
  # new_grads, total_norm = tf.clip_by_global_norm(grads, xxx) 保持整体缩放方向不变，缩小到xxx
  

• 高阶操作

  # tf.where(tensor) : tensor只能是一个bool类型的。会将True位置的坐标返回
  # tf.where(tensor, A, B) : tensor只能是一个bool类型的。如果为True，在A上采样，如果为False在B上采样
  # tf.scatter_nd(indices, updates, shape) : 更新操作。但是只能在底板上更新，也就是初始化为0。根绝indices的坐标指示，把updates的数据跟新到shape这个底板上面去。
  
  # y = tf.linspace(start, end, nums) : 分割
  # x = tf.linspace(start, end, nums)
  # point_x, point_y = tf.meshgrid(x, y) : 切分表格