09. Tensorflow2.0 前向传播（张量）实战

1. 前向传播案例

1.1. 代码实现

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

# 加载数据集
# x: [60k, 28, 28]
# y: [60k]  0~9
(x, y), _ = datasets.mnist.load_data()
# x:[0~255] => [0~1.]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)

print(x.shape, y.shape, x.dtype, y.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))

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

# truncated_normal 待裁剪功能
# [b, 784] => [b, 256] => [b, 128] => [b, 10]
# w: [dim_in, dim_out]
# bias: [dim_out]
# 注意： 求梯度的时候必须用tf.Variable
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]))

# 定义学习率 10^-3
lr = 1e-3

for epoch in range(10): # iterate db for 10
    for step, (x, y) in enumerate(train_db):  # for every batch
        # x: [128, 28, 28]
        # y: [128]

        # [b, 28, 28] => [b, 28*28]
        x = tf.reshape(x, [-1, 28*28])

        with tf.GradientTape() as tape:
            # x: [b, 28*28]
            # h1 = x@w1 + b1
            # [b, 784] @ [784, 256] + [256] => [b, 256]
            h1 = tf.matmul(x, w1) + b1
            h1 = tf.nn.relu(h1)
            h2 = tf.matmul(h1, w2) + b2
            h2 = tf.nn.relu(h2)
            out = tf.matmul(h2, w3) + b3

            # compute loss
            # out: [b, 10]
            # y: [b]
            y_onehot = tf.one_hot(y, depth=10)

            # 均方误差
            # mse = mean(sum(y - out)^2)
            loss = tf.square(y_onehot - out)

            loss = tf.reduce_mean(loss)

        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # w1 = w1 - lr * w1_grads   会生成新的tensor
        # w1.assign_sub(lr * grads[0]) 原地计算
        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(epoch, "--> ", step, 'loss:', float(loss))

1.2. 梯度爆炸解决方案

• 调整学习率
• 调整参数
  

2. 需要全套课程视频+PPT+代码资源可以私聊我-

• 方式1：CSDN私信我!
• 方式2：QQ邮箱:594042358@qq.com或者直接加我QQ: 594042358!