docs/en/datasets/classify/caltech101.md
The Caltech-101 dataset is a classic image classification benchmark of 9,144 images spanning 101 object categories plus one background class. Each category holds about 40 to 800 images of real-world objects — animals, vehicles, household items, and people — making it a compact yet challenging benchmark for object recognition models.
<p align="center"> <iframe loading="lazy" width="720" height="405" src="https://www.youtube.com/embed/isc06_9qnM0" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen> </iframe><strong>Watch:</strong> How to Train <a href="https://www.ultralytics.com/glossary/image-classification">Image Classification</a> Model using Caltech-101 Dataset with Ultralytics Platform
</p>!!! note "Automatic Data Splitting"
Caltech-101 ships without a predefined train/validation split. The training commands below automatically split it 80% train / 20% validation, so no manual preparation is needed.
BACKGROUND_Google class (102 class folders in total).Caltech-101 is distributed as 102 folders — one per class, covering 101 object categories plus a BACKGROUND_Google class — with no predefined train/validation split. When you launch training, Ultralytics automatically partitions the images so models train across all 102 classes without any manual setup:
Caltech-101 is widely used to train and evaluate image classification and object recognition models, including Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). Its broad category coverage and clean, labeled images make it a popular benchmark for machine learning and computer vision research and prototyping.
Train a YOLO model on Caltech-101 for 100 epochs at an image size of 416. For the full list of available arguments, see the Training page and the image classification task guide.
!!! example "Train Example"
=== "Python"
```python
from ultralytics import YOLO
# Load a model
model = YOLO("yolo26n-cls.pt") # load a pretrained model (recommended for training)
# Train the model
results = model.train(data="caltech101", epochs=100, imgsz=416)
```
=== "CLI"
```bash
# Start training from a pretrained *.pt model
yolo classify train data=caltech101 model=yolo26n-cls.pt epochs=100 imgsz=416
```
The Caltech-101 dataset contains high-quality color images of various objects, providing a well-structured dataset for image classification tasks. Here are some examples of images from the dataset:
The samples show the variety of categories and the natural, centered framing typical of Caltech-101, which makes it a clean starting point for training robust object recognition models.
If you use the Caltech-101 dataset in your research or development work, please cite the following paper:
!!! quote ""
=== "BibTeX"
```bibtex
@article{fei2007learning,
title={Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories},
author={Fei-Fei, Li and Fergus, Rob and Perona, Pietro},
journal={Computer vision and Image understanding},
volume={106},
number={1},
pages={59--70},
year={2007},
publisher={Elsevier}
}
```
We would like to acknowledge Li Fei-Fei, Rob Fergus, and Pietro Perona for creating and maintaining the Caltech-101 dataset as a valuable resource for the machine learning and computer vision research community. For more information about the Caltech-101 dataset and its creators, visit the Caltech-101 dataset website.
The Caltech-101 dataset is widely used to train and benchmark image classification and object recognition models. It contains 9,144 images across 101 object categories plus a background class, providing a challenging benchmark for evaluating algorithms such as Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs).
To train an Ultralytics YOLO model on Caltech-101, use the code snippets below. The dataset downloads automatically on first use. For a full list of arguments, see the model Training page.
!!! example "Train Example"
=== "Python"
```python
from ultralytics import YOLO
# Load a model
model = YOLO("yolo26n-cls.pt") # load a pretrained model (recommended for training)
# Train the model
results = model.train(data="caltech101", epochs=100, imgsz=416)
```
=== "CLI"
```bash
# Start training from a pretrained *.pt model
yolo classify train data=caltech101 model=yolo26n-cls.pt epochs=100 imgsz=416
```
Caltech-101 contains 101 object categories plus one BACKGROUND_Google class, for 102 class folders and 9,144 images in total. When you train with Ultralytics, the model learns all 102 classes. Category sizes are imbalanced, ranging from about 40 to 800 images each.
Caltech-101 has no predefined split. The first time you train, Ultralytics automatically divides it 80% training / 20% validation — about 7,280 training and 1,864 validation images — so you do not need to create splits manually. To control the split yourself, organize the images into train/ and val/ folders before training.
Yes. Ultralytics Platform lets you manage datasets, train image classification models, and deploy them without extensive coding. It is a convenient way to run Caltech-101 experiments in the cloud, and you can explore more options in our classification datasets overview.