커피 한잔 사주세요😄
*내 게시물은 Fashion-MNIST를 설명합니다.
FashionMNIST()는 아래와 같이 Fashion-MNIST 데이터세트를 사용할 수 있습니다.
*메모:
from torchvision.datasets import FashionMNIST train_data = FashionMNIST( root="data" ) train_data = FashionMNIST( root="data", train=True, transform=None, target_transform=None, download=False ) test_data = FashionMNIST( root="data", train=False ) len(train_data), len(test_data) # (60000, 10000) train_data # Dataset FashionMNIST # Number of datapoints: 60000 # Root location: data # Split: Train train_data.root # 'data' train_data.train # True print(train_data.transform) # None print(train_data.target_transform) # None train_data.download # <bound method MNIST.download of Dataset FashionMNIST # Number of datapoints: 60000 # Root location: data # Split: Train> len(train_data.classes) # 10 train_data.classes # ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', # 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] train_data[0] # (<PIL.Image.Image image mode=L size=28x28>, 9) train_data[1] # (<PIL.Image.Image image mode=L size=28x28>, 0) train_data[2] # (<PIL.Image.Image image mode=L size=28x28>, 0) train_data[3] # (<PIL.Image.Image image mode=L size=28x28>, 3) train_data[4] # (<PIL.Image.Image image mode=L size=28x28>, 0) import matplotlib.pyplot as plt def show_images(data, main_title=None): plt.figure(figsize=(8, 4)) plt.suptitle(t=main_title, y=1.0, fontsize=14) for i, (image, label) in enumerate(data, 1): plt.subplot(2, 5, i) plt.tight_layout() plt.title(label) plt.imshow(image) if i == 10: break plt.show() show_images(data=train_data, main_title="train_data") show_images(data=test_data, main_title="test_data")
위 내용은 PyTorch의 FashionMNIST의 상세 내용입니다. 자세한 내용은 PHP 중국어 웹사이트의 기타 관련 기사를 참조하세요!