Originally created for Stanford’s course, this dataset is a scaled-down version of the massive ImageNet database, designed to be more manageable for training models on standard hardware while remaining complex enough for meaningful research. Content: 120,000 total images.
200 distinct categories (e.g., animals, vehicles, everyday objects). Image Resolution: pixels (full-color JPEG format). Data Split: Training: 100,000 images (500 per class). Validation: 10,000 images (50 per class). Test: 10,000 images (unlabeled). Implementation Details COLLECTION PICS 200zip
: Contains the WordNet IDs (unique identifiers) for the 200 classes. Originally created for Stanford’s course, this dataset is
: Organized into 200 subdirectories, each containing 500 images for that specific class. Image Resolution: pixels (full-color JPEG format)
When working with the tiny-imagenet-200.zip file, developers typically use a custom data loader to handle the folder structure. Below is a conceptual breakdown of the typical file organization:
: Maps those WordNet IDs to human-readable labels (e.g., "n02124075" becomes "Egyptian cat").
Вся информация, представленная на сайте, является демонстрационной. Ваши персональные данные необходимы исключительно для корректной обработки и отправки заказов и не будут переданы третьим лицам.
Мы используем файлы cookie для вашего удобства пользования сайтом и повышения качества рекомендаций. Подробнее
