DataLoader
- dataset:数据
- batch_size:每次取几张img
- shuffle:打乱
- num_workers:多进程(默认是0)
- drop_last:多余的要不要舍去
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 准备的测试数据集
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor())
# 加载数据
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True, num_workers=0, drop_last=True)
# 测试数据集中的第一张图片
img, target = test_data[0]
print(img.shape)
print(target)
tensorboard显示
writer = SummaryWriter("dataloader")
step = 0
# 取出test_loader中的每一个返回
for data in test_loader:
imgs, targets = data
# print(imgs.shape)
# print(targets)
writer.add_images("test_data_drop_last", imgs, step)
step = step + 1
结果
drop_last=False(除不尽的不会舍去)
drop_last=True(除不尽的舍去)
shuffle
# 准备的测试数据集
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor())
# 加载数据
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=False, num_workers=0, drop_last=True)
# 测试数据集中的第一张图片
img, target = test_data[0]
print(img.shape)
print(target)
writer = SummaryWriter("dataloader")
# 取出test_loader中的每一个返回
for epoch in range(2):
step = 0
for data in test_loader:
imgs, targets = data
writer.add_images("Epoch: {}".format(epoch), imgs, step)
step = step + 1
writer.close()
结果
shuffle=False(不打乱)
shuffle=True(打乱)