3.9 多层感知机的从零开始实现

代码实现

import tensorflow as tf
import numpy as np
import tensorflow_utils as tf_utils

from tensorflow.keras.datasets import fashion_mnist
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
batch_size = 256
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
x_train = x_train/255.0
x_test = x_test/255.0
train_iter = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(batch_size)
test_iter = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(batch_size)

# 定义模型参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = tf.Variable(tf.random.normal(shape=(num_inputs, num_hiddens),mean=0, stddev=0.01, dtype=tf.float32))
b1 = tf.Variable(tf.zeros(num_hiddens, dtype=tf.float32))
W2 = tf.Variable(tf.random.normal(shape=(num_hiddens, num_outputs),mean=0, stddev=0.01, dtype=tf.float32))
b2 = tf.Variable(tf.random.normal([num_outputs], stddev=0.1))

# 定义激活函数
def relu(x):
    return tf.math.maximum(x,0)

# 定义模型
def net(X):
    X = tf.reshape(X, shape=[-1, num_inputs])
    h = relu(tf.matmul(X, W1) + b1)
    return tf.math.softmax(tf.matmul(h, W2) + b2)

# 定义损失函数
def loss(y_hat,y_true):
    return tf.losses.sparse_categorical_crossentropy(y_true,y_hat)

# 训练模型
num_epochs, lr = 5, 0.5
params = [W1, b1, W2, b2]
tf_utils.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)

输出

epoch 1, loss 0.7878, train acc 0.703, test acc 0.816
epoch 2, loss 0.4814, train acc 0.821, test acc 0.838
epoch 3, loss 0.4160, train acc 0.845, test acc 0.851
epoch 4, loss 0.3834, train acc 0.857, test acc 0.859
epoch 5, loss 0.3610, train acc 0.866, test acc 0.864