EMNIST in PyTorch

explains can use EMNIST dataset as shown below:

*Memos:

• The 1st argument is root(Required-Type:str or pathlib.Path). *An absolute or relative path is possible.


• The 2nd argument is split(Required-Type:str). *"byclass", "bymerge", "balanced", "letters", "digits" or "mnist" can be set to it.


• There is train argument(Optional-Default:False-Type:float):
  *Memos:
  
  
  
  
  • For split="byclass" and split="byclass", if it's True, train data(697,932 images) is used while if it's False, test data(116,323 images) is used.
  
  
  • For split="balanced", if it's True, train data(112,800 images) is used while if it's False, test data(188,00 images) is used.
  
  
  • For split="letters", if it's True, train data(124,800 images) is used while if it's False, test data(20,800 images) is used.
  
  
  • For split="digits", if it's True, train data(240,000 images) is used while if it's False, test data(40,000 images) is used.
  
  
  • For split="mnist", if it's True, train data(60,000 images) is used while if it's False, test data(10,000 images) is used.
  
  
  
  
  
  



• There is transform argument(Optional-Default:None-Type:callable).



• There is target_transform argument(Optional-Default:None-Type:callable).



• There is download argument(Optional-Default:False-Type:bool):
  *Memos:
  
  
  
  
  • If it's True, the dataset is downloaded from the internet and extracted(unzipped) to root.
  
  
  • If it's True and the dataset is already downloaded, it's extracted.
  
  
  • If it's True and the dataset is already downloaded and extracted, nothing happens.
  
  
  • It should be False if the dataset is already downloaded and extracted because it's faster.
  
  
  • You can manually download and extract the dataset from
    
    
    
    
    
    
    

    CODE Kopieren

    from torchvision.datasets import EMNIST
    
    from torchvision.transforms import v2
    
    
    
    train_data = EMNIST(
    
        root="data",
    
        split="byclass",
    
        train=True,
    
        transform=v2.Compose([
    
            v2.RandomHorizontalFlip(p=1.0),
    
            v2.RandomRotation(degrees=(90, 90))
    
        ])
    
    )
    
    
    
    test_data = EMNIST(
    
        root="data",
    
        split="byclass",
    
        train=False,
    
        transform=v2.Compose([
    
            v2.RandomHorizontalFlip(p=1.0),
    
            v2.RandomRotation(degrees=(90, 90))
    
        ])
    
    )
    
    
    
    import matplotlib.pyplot as plt
    
    
    
    def show_images(data):
    
        plt.figure(figsize=(12, 2))
    
        col = 5
    
        for i, (image, label) in enumerate(data, 1):
    
            plt.subplot(1, col, i)
    
            plt.title(label)
    
            plt.imshow(image)
    
            if i == col:
    
                break
    
        plt.show()
    
    
    
    show_images(data=train_data)
    
    show_images(data=test_data)
    
    

    
    
    
    
    
    
    
    

    

    Vollständiger Original-Bericht

    Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.

    ↗ Original-Artikel auf dev.to lesen