# Caltech 256 Dataset - Classification of Images — Data

来源：https://www.kaggle.com/competitions/caltech-256-image-classification/data

采集时间：2026-10-19T09:08:15Z

## Context
The Caltech 256 is considered an improvement to its predecessor, the Caltech 101 dataset, with new features such as larger category sizes, new and larger clutter categories, and overall increased difficulty. This is a great dataset to train models for visual recognition: How can we recognize toasters, cell phones, skyscrapers, sail boats, speed boats and many other categories in cluttered pictures? How can we classify images in these categories?

## Content
There are 30,607 images in this dataset spanning 256 object categories. Object categories are extremely diverse, ranging from vehicles to computer monitor to tuning fork to watch to skyscraper to guitar. 

## Acknowledgements
Original data source and banner image: http://www.vision.caltech.edu/Image_Datasets/Caltech256/

When using this dataset, please remember to cite:

Griffin, G. Holub, AD. Perona, P.
The Caltech 256.
Caltech Technical Report.

## Inspiration
Can you build a model that classifies images in the Caltech-256 dataset into their respective categories?
For example, by taking input as an image, can your deep learning model (a Convolutional Neural Network ) classify whether the object is a ostrich, fried egg, leopard, skyscraper, penguin, or one of the other 251 object categories?

## Files

*   **Caltech 256_Test** - the test set
*   **Caltech 256_Train** - the training set
*   **sample_submission.csv** - a sample submission file in the correct format


## Columns of the sample submission file

*   `img_path` - path of the image
*   `label` - category/class of the object/image