第6章 TensorFlow 实现与训练

目标

用框架实现神经网络。

---

必学内容

TensorFlow/Keras 基础

model = Sequential([
    Dense(25, activation='relu'),
    Dense(15, activation='relu'),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy')
model.fit(X, y, epochs=100)

NumPy 手写前向传播

def forward(x, W1, b1, W2, b2):
    z1 = np.dot(W1, x) + b1
    a1 = np.maximum(0, z1)  # ReLU
    z2 = np.dot(W2, a1) + b2
    a2 = sigmoid(z2)
    return a2

---

必须真正理解

每一层在做什么

层1：提取低级特征
层2：提取中级特征
层3：组合成最终判断

---

Python Example

Included in the static site for reading. Run locally from the source repository when needed.

""" 第6章：TensorFlow/Keras 实现神经网络 Chapter 6: Neural Network with TensorFlow/Keras """ import numpy as np import tensorflow as tf from tensorflow.keras import Sequential from tensorflow.keras.layers import Dense from sklearn.datasets import make_classification from sklearn.model_selection import train_test_split # 数据 X, y = make_classification(n_samples=1000, n_features=20, n_classes=2, random_state=42) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) # Keras 模型 model = Sequential([ Dense(25, activation='relu', input_shape=(20,), name='hidden1'), Dense(15, activation='relu', name='hidden2'), Dense(1, activation='sigmoid', name='output') ]) model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) model.summary() print("\n开始训练...") history = model.fit(X_train, y_train, epochs=20, batch_size=32, validation_split=0.1, verbose=0) loss, acc = model.evaluate(X_test, y_test, verbose=0) print(f"\n测试集准确率: {acc:.4f}") # 对比：不用框架时参数量 print(f"\n模型总参数量: {model.count_params()}") print("对比 NumPy 手写：你需要手动管理 W1,b1,W2,b2 的维度和更新")