3.5 圖像分類數據集（Fashion-MNIST）

Fashion-MNIST

本數據集是每張圖片大小28*28的灰度圖像，共有70000張，其中包含60,000個示例的訓練集和10,000個示例的測試集，10種標籤
比手寫體數據集更具挑戰性，適合初學者（我）學習

代碼實現

import tensorflow as tf
from tensorflow import keras
import numpy as np
import time
import sys
import matplotlib.pyplot as plt

from tensorflow.keras.datasets import fashion_mnist

(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()


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):
    _, figs = plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.reshape((28, 28)))
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()


X, y = [], []
for i in range(10):
    X.append(x_train[i])
    y.append(y_train[i])
show_fashion_mnist(X, get_fashion_mnist_labels(y))

batch_size = 256
if sys.platform.startswith('win'):
    num_workers = 0  # 0表示不用額外的進程來加速讀取數據
else:
    num_workers = 4
train_iter = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(batch_size) # 加載數據集，batch_size 小批量加載，batch_size是一個超參數

# 查看讀取一遍訓練數據需要的時間
start = time.time()
for X, y in train_iter:
    continue
print('%.2f sec' % (time.time() - start))

輸出

0.12 sec

相關注解

函數作用：不顯示x、y軸座標

f.axes.get_xaxis().set_visible(False)
f.axes.get_yaxis().set_visible(False)

tf.data.Dataset.from_tensor_slices 進行加載數據集

train_iter = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(batch_size)