3.6 softmax迴歸的從零開始實現

代碼實現

import tensorflow as tf
import numpy as np

from tensorflow.keras.datasets import fashion_mnist

batch_size=256
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_train = tf.cast(x_train, tf.float32) / 255 #在進行矩陣相乘時需要float型，故強制類型轉換爲float型
x_test = tf.cast(x_test,tf.float32) / 255 #在進行矩陣相乘時需要float型，故強制類型轉換爲float型
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)

num_inputs = 784
num_outputs = 10
W = tf.Variable(tf.random.normal(shape=(num_inputs, num_outputs), mean=0, stddev=0.01, dtype=tf.float32))
b = tf.Variable(tf.zeros(num_outputs, dtype=tf.float32))

def softmax(logits, axis=-1): # softmax運算
    return tf.exp(logits)/tf.reduce_sum(tf.exp(logits), axis, keepdims=True)

def net(X): # 定義模型
    logits = tf.matmul(tf.reshape(X, shape=(-1, W.shape[0])), W) + b
    return softmax(logits)

def cross_entropy(y_hat, y): # 交叉熵損失函數
    y = tf.cast(tf.reshape(y, shape=[-1, 1]),dtype=tf.int32)
    y = tf.one_hot(y, depth=y_hat.shape[-1])
    y = tf.cast(tf.reshape(y, shape=[-1, y_hat.shape[-1]]),dtype=tf.int32)
    return -tf.math.log(tf.boolean_mask(y_hat, y)+1e-8)

def accuracy(y_hat, y): # 計算分類準確率
    return np.mean((tf.argmax(y_hat, axis=1) == y))

# 描述,對於tensorflow2中，比較的雙方必須類型都是int型，所以要將輸出和標籤都轉爲int型
def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for _, (X, y) in enumerate(data_iter):
        y = tf.cast(y,dtype=tf.int64)
        acc_sum += np.sum(tf.cast(tf.argmax(net(X), axis=1), dtype=tf.int64) == y)
        n += y.shape[0]
    return acc_sum / n

num_epochs, lr = 5, 0.1

def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params=None, lr=None, trainer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            with tf.GradientTape() as tape:
                y_hat = net(X)
                l = tf.reduce_sum(loss(y_hat, y))
            grads = tape.gradient(l, params)
            if trainer is None:
                # 如果沒有傳入優化器，則使用原先編寫的小批量隨機梯度下降
                for i, param in enumerate(params):
                    param.assign_sub(lr * grads[i] / batch_size)
            else:
                # tf.keras.optimizers.SGD 直接使用是隨機梯度下降 theta(t+1) = theta(t) - learning_rate * gradient
                # 這裏使用批量梯度下降，需要對梯度除以 batch_size
                trainer.apply_gradients(zip([grad / batch_size for grad in grads], params))

            y = tf.cast(y, dtype=tf.float32)
            train_l_sum += l.numpy()
            train_acc_sum += tf.reduce_sum(tf.cast(tf.argmax(y_hat, axis=1) == tf.cast(y, dtype=tf.int64), dtype=tf.int64)).numpy()
            n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

trainer = tf.keras.optimizers.SGD(lr)
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)

import matplotlib.pyplot as plt
X, y = iter(test_iter).next()

def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]

def show_fashion_mnist(images, labels):
    # 這⾥的_表示我們忽略（不使⽤）的變量
    _, figs = plt.subplots(1, len(images), figsize=(12, 12)) # 這裏注意subplot 和subplots 的區別
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(tf.reshape(img, shape=(28, 28)).numpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()

true_labels = get_fashion_mnist_labels(y.numpy())
pred_labels = get_fashion_mnist_labels(tf.argmax(net(X), axis=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

show_fashion_mnist(X[0:9], titles[0:9])

輸出

epoch 1, loss 0.7841, train acc 0.750, test acc 0.793
epoch 2, loss 0.5709, train acc 0.812, test acc 0.812
epoch 3, loss 0.5257, train acc 0.825, test acc 0.819
epoch 4, loss 0.5014, train acc 0.832, test acc 0.825
epoch 5, loss 0.4856, train acc 0.836, test acc 0.827