专栏推荐

正文

train_db = datasets.MNIST('../data', train=True, download=True,

transform=transforms.Compose([

transforms.ToTensor(),

transforms.Normalize((0.1307,), (0.3081,))

]))

test_db = datasets.MNIST('../data', train=False, transform=transforms.Compose([

transforms.ToTensor(),

transforms.Normalize((0.1307,), (0.3081,))

]))

train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000])

train_loader = torch.utils.data.DataLoader(train_db,batch_size=batch_size, shuffle=True)

val_loader = torch.utils.data.DataLoader(val_db,batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(test_db,batch_size=batch_size, shuffle=True)

閱讀更多 幻風的AI之路 的文章

關鍵字: 人工智能 神经网络 训练样本