3.2tensorflow2.0中幾個簡單常用的圖檔資料集介紹及加載方式

代碼會檢查有沒有資料集在本地，沒有資料集的話代碼會自動下載下傳，注意科學上網提高下載下傳速度

MNIST資料集

• 一個手寫數字資料集，共10類

from tensorflow import keras

(x_train,y_train),(x_test,y_test)=keras.datasets.mnist.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (60000, 28, 28) (60000,) (10000, 28, 28) (10000,)      

Fashion_MNIST

• 一個服裝資料集，共10類

(x_train,y_train),(x_test,y_test)=keras.datasets.fashion_mnist.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (60000, 28, 28) (60000,) (10000, 28, 28) (10000,)      

Cifar10/100

• 一個各類東西的資料集，cifar10和cifar100資料集圖檔是一樣的，隻是cifar100在cifar10上的10個類别的基礎上，在每個小類别裡又劃分成了新的10類，共10*10=100類

(x_train,y_train),(x_test,y_test)=keras.datasets.cifar10.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (50000, 32, 32, 3) (50000, 1) (10000, 32, 32, 3) (10000, 1)

(x_train,y_train),(x_test,y_test)=keras.datasets.cifar100.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (50000, 32, 32, 3) (50000, 1) (10000, 32, 32, 3) (10000, 1)