第一篇 基本操作 01 Tensor数据类型 02 创建Tensor 03 Tensor索引和切片 04 维度变换 05 Broadcasting 06 数学运算 07 前向传播(张量)- 实战 第二篇 高级操作 08 合并与分割 09 数据统计 10 张量排序 11 填充与复制 12 张量限幅 13 高阶操作 第三篇 神经网络与全连接层 14 数据加载 15 测试(张量)- 实战 16 全连接层 17 输出方式 18 误差计算 第四篇 随机梯度下降 19 梯度下降简介 20 激活函数及其梯度

import tensorflow as tf from tensorflow import keras from keras import Sequential,datasets, layers, optimizers, metrics def preprocess(x, y): """数据处理函数""" x = tf.cast(x, dtype=tf.float32) / 255. y = tf.cast(y, dtype=tf.int32)

import numpy as np import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D def himmeblau(x): return (x[0]**2 + x[1] - 11)**2 + (x[0] + x[1]**2 - 7)**2 x = np.arange(-6, 6, 0.1) y = np.arange(-6, 6, 0.1) print(f'x_shape: {x.shape},y_sh

import tensorflow as tf x = tf.constant(1.) w1 = tf.constant(2.) b1 = tf.constant(1.) w2 = tf.constant(2.) b2 = tf.constant(1.) with tf.GradientTape(persistent=True) as tape: tape.watch([w1, b1, w2, b2]) y1 = x * w1 + b1 y2 = y1 * w2 + b2 dy2_dy1 = t

import tensorflow as tf x = tf.random.normal([2, 4]) w = tf.random.normal([4, 3]) b = tf.zeros([3]) y = tf.constant([2, 0]) with tf.GradientTape() as tape: tape.watch([w, b]) # axis=1,表示结果[b,3]中的3这个维度为概率 prob = tf.nn.softmax(x @ w + b, axis=1) # 2 --

import tensorflow as tf x = tf.random.normal([1, 3]) w = tf.ones([3, 1]) b = tf.ones([1]) y = tf.constant([1]) with tf.GradientTape() as tape: tape.watch([w, b]) prob = tf.sigmoid(x @ w + b) loss = tf.reduce_mean(tf.losses.MSE(y, prob)) grads = tape.

import tensorflow as tf x = tf.random.normal([2, 4]) w = tf.random.normal([4, 3]) b = tf.zeros([3]) y = tf.constant([2, 0]) with tf.GradientTape() as tape: tape.watch([w, b]) prob = tf.nn.softmax(x @ w + b, axis=1) loss = tf.reduce_mean(tf.losses.MSE

import tensorflow as tf a = tf.linspace(-10., 10., 10) a with tf.GradientTape() as tape: tape.watch(a) y = tf.sigmoid(a) grads = tape.gradient(y, [a]) grads a = tf.linspace(-5.,5.,10) a tf.tanh(a) a = tf.linspace(-1.,1.,10) a tf.nn.relu(a) tf.nn.leak

import tensorflow as tf w = tf.constant(1.) x = tf.constant(2.) y = x * w with tf.GradientTape() as tape: tape.watch([w]) y2 = x * w grad1 = tape.gradient(y, [w]) grad1 with tf.GradientTape() as tape: tape.watch([w]) y2 = x * w grad2 = tape.gradient(

import tensorflow as tf y = tf.constant([1, 2, 3, 0, 2]) y = tf.one_hot(y, depth=4) # max_label=3种 y = tf.cast(y, dtype=tf.float32) out = tf.random.normal([5, 4]) out loss1 = tf.reduce_mean(tf.square(y - out)) loss1 loss2 = tf.square(tf.norm(y - out)

sigmoid out' = sigmoid(out) # 把输出值压缩在0-1 import tensorflow as tf a = tf.linspace(-6., 6, 10) a tf.sigmoid(a) x = tf.random.normal([1, 28, 28]) * 5 tf.reduce_min(x), tf.reduce_max(x) x = tf.sigmoid(x) tf.reduce_min(x), tf.reduce_max(x) a = tf.linspace

out = f(X@W + b) out = relut(X@W + b) import tensorflow as tf x = tf.random.normal([4, 784]) net = tf.keras.layers.Dense(512) out = net(x) out.shape net.kernel.shape, net.bias.shape net = tf.keras.layers.Dense(10) try: net.bias except Exception as e:

import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets import os # do not print irrelevant information # os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # x: [60k,28,28], [10,28,28] # y: [60k], [10k] (x, y), (x_test, y_te

import tensorflow as tf from tensorflow import keras # train: 60k | test: 10k (x, y), (x_test, y_test) = keras.datasets.mnist.load_data() x.shape y.shape # 0纯黑.255纯白 x.min(), x.max(), x.mean() x_test.shape, y_test.shape # 0-9有10种分类结果 y_onehot = tf.on

import tensorflow as tf a = tf.random.normal([3, 3]) a mask = a > 0 mask # 为True元素,即>0的元素的索引 indices = tf.where(mask) indices # 取回>0的值 tf.gather_nd(a, indices) A = tf.ones([3, 3]) B = tf.zeros([3, 3]) # True的元素会从A中选值,False的元素会从B中选值 tf.where(mask,

import tensorflow as tf a = tf.range(10) a # a中小于2的元素值为2 tf.maximum(a, 2) # a中大于8的元素值为8 tf.minimum(a, 8) # a中的元素值限制在[2,8]区间内 tf.clip_by_value(a, 2, 8) a = a - 5 a tf.nn.relu(a) tf.maximum(a, 0) 缩放时不改变梯度方向 a = tf.random.normal([2, 2], mean=10) a tf.no

import tensorflow as tf a = tf.reshape(tf.range(9), [3, 3]) a tf.pad(a, [[0, 0], [0, 0]]) tf.pad(a, [[ 1, 0, ], [0, 0]]) tf.pad(a, [[1, 1], [0, 0]]) tf.pad(a, [[1, 1], [1, 0]]) tf.pad(a, [[1, 1], [1, 1]]) a = tf.random.normal([4, 28, 28, 3]) a.shape

import tensorflow as tf a = tf.random.shuffle(tf.range(5)) a tf.sort(a, direction='DESCENDING') # 返回索引 tf.argsort(a, direction='DESCENDING') idx = tf.argsort(a, direction='DESCENDING') tf.gather(a, idx) idx = tf.argsort(a, direction='DESCENDING') tf.

import tensorflow as tf a = tf.ones([2, 2]) a tf.norm(a) tf.sqrt(tf.reduce_sum(tf.square(a))) a = tf.ones([4, 28, 28, 3]) a.shape tf.norm(a) tf.sqrt(tf.reduce_sum(tf.square(a))) b = tf.ones([2, 2]) tf.norm(b) tf.norm(b, ord=2, axis=1) tf.norm(b, ord=