使用GradientTape训练基本TensorFlow模型

import tensorflow as tf

# 定义模型的参数
w = tf.Variable(2.0)
b = tf.Variable(1.0)

# 定义模型的前向传播函数
def forward(x):
    return w * x + b

# 定义损失函数
def loss(y_true, y_pred):
    return tf.reduce_mean(tf.square(y_true - y_pred))

# 定义训练数据
x_train = [1, 2, 3, 4]
y_train = [3, 5, 7, 9]

# 定义训练循环
learning_rate = 0.01
epochs = 100

for epoch in range(epochs):
    with tf.GradientTape() as tape:
        # 计算当前参数下的预测值
        y_pred = forward(x_train)
        # 计算当前参数下的损失值
        current_loss = loss(y_train, y_pred)
    
    # 计算当前参数下的梯度
    dw, db = tape.gradient(current_loss, [w, b])
    
    # 更新参数
    w.assign_sub(learning_rate * dw)
    b.assign_sub(learning_rate * db)
    
    # 打印训练过程中的损失值
    print(f"Epoch {epoch+1}: Loss = {current_loss.numpy()}")