How to use common datasets in pytorch

---

about pytorch Use of data sets , The sample code is as follows ：

from torch.utils.tensorboard import SummaryWriter
from torchvision.transforms import Compose
from torchvision import transforms
import torchvision
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

dataset_transform = Compose([transforms.ToTensor()])


#  The use of official data sets is still the key pytorch Official documents of 
train_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=True,transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=False,transform=dataset_transform,download=True)

#  View the first data in the test data set 
# print(test_set[0])
#  View the classification in the test data set 
# print(test_set.classes)
#
#  Take out the picture in the first data （img） And classification results （target）
# img,target = test_set[0]
#  View the type of picture data 
# print(img)
# print(target)
#  Output category 
# print(test_set.classes[target])
#  view picture 
# img.show()

#  Use tensorboard Show tensor Pictures of data types 
writer = SummaryWriter("logs")
for i in range(10):
	#  Take out the picture in the data （img） And classification results （target）
    img,target = test_set[i]
    writer.add_image("test_set",img,i)

writer.close()

The above code results in tensorboard visualization ：

Code train_set = torchvision.datasets.CIFAR10(root="./CIFAR10",train=True,transform=dataset_transform,download=True) Explanation of common parameters in

root: root directory , Where to store the data set 
train: if True, It is divided into training data sets , if False, It is divided into test data sets 
transform： Specify how the input dataset is processed 
download: if True, The data set will be downloaded to root Under the specified directory , Otherwise it won't download 

Official documents Interpretation of parameters ：

• root (string) – Root directory of dataset where directory cifar-10-batches-py exists or will be saved to if download is set to True.

• train (bool, optional) – If True, creates dataset from training set, otherwise creates from test set.

• transform (callable, optional) – A function/transform that takes in an PIL image and returns a transformed version. E.g, transforms.RandomCrop

• target_transform (callable, optional) – A function/transform that takes in the target and transforms it.

• download (bool, optional) – If true, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again.

Be careful

• The use of official data sets is still the key pytorch Official documents of
• Download the details of the dataset ： Know the download link （ The download link can be viewed in the source code ） Then you can download without using the code , Using thunderbolt to download may be faster .
• Learn to use Pycharm Medium ctrl+p and ctrl+alt Both shortcuts
• pytorch Official website
• pytorch Official data set （ Download dataset method ）