从张量流模型中获取结果

import tensorflow as tf

# 定义输入数据和标签
x_train = [1.0, 2.0, 3.0, 4.0]
y_train = [0.0, -1.0, -2.0, -3.0]

# 定义模型参数
W = tf.Variable([0.3], dtype=tf.float32)
b = tf.Variable([-0.3], dtype=tf.float32)

# 定义输入和输出的占位符
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)

# 构建线性模型
linear_model = W * x + b

# 定义损失函数
loss = tf.reduce_sum(tf.square(linear_model - y))

# 定义优化器
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)

# 初始化变量
init = tf.global_variables_initializer()

# 创建会话并运行模型
with tf.Session() as sess:
    sess.run(init)  # 初始化变量
    for epoch in range(1000):
        sess.run(train, {x: x_train, y: y_train})

    # 获取模型参数
    current_W, current_b = sess.run([W, b])
    print("W: %s b: %s" % (current_W, current_b))

    # 使用模型进行预测
    predict_x = 5.0
    predicted_y = sess.run(linear_model, {x: predict_x})
    print("Predicted y for x = %.1f: %.1f" % (predict_x, predicted_y))