pytorch学习（四）：Dataloader使用

dataset：读取数据

dataloader：加载器，把数据加载到神经网络当中。从dataset中取数据。

import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
dataset_transform=torchvision.transforms.Compose([
    torchvision.transforms.ToTensor(),

])
test_data=torchvision.datasets.CIFAR10('./dataset',train=False,transform=dataset_transform,download=True)
test_loader=DataLoader(dataset=test_data,batch_size=64,shuffle=True,num_workers=0,drop_last=False)
#测试数据集中第一张图片及targeit
img,target = test_data[0]
print(img.shape)
print(target)
#imgs=img[0],img[1],img[2],img[3]
#targets=target[0],target[1],target[2],target[3]
writer=SummaryWriter("dataloader")
for epoch in range(2):
    step=0
    for data in test_loader:
        imgs,targets=data
        print(imgs.shape)
        writer.add_images("Epoch:{}".format(epoch),imgs,step)
        step=step+1
writer.close()

遇见问题：writer.add_image()报错。报错原因：应该都是write.add_images()

二者区别：

Tensor with :math:`(1, H, W)`, :math:`(H, W)`, :math:`(H, W, 3)` is also suitable as long as

img_tensor: Default is :math:`(N, 3, H, W)`. If ``dataformats`` is specified, other shape will be

write.add_images() 是添加多张图片。