Caltech 101 Dataset

Estimated reading: 3 minutes 2596 views

Visualization of Caltech 101 Dataset in the Deep Lake UI

Caltech 101 Dataset

What is Caltech 101 Dataset?

The Caltech 101 dataset contains 101 categories of objects for recognition algorithms. Each category has about 40 to 800 images. The dataset contains 50 categories on average per category. The images in this dataset are roughly 300 x 200 pixels.

Downloading Caltech 101 Dataset in Python

Instead of downloading the Caltech 101 in Python, you can effortlessly load it in Python via our Deep Lake open-source with just one line of code.

Load Caltech 101 Dataset Subset in Python

				
					import deeplake
ds = deeplake.load('hub://activeloop/caltech101')

Caltech 101 Dataset Structure

Data Fields

images: tensor containing the image.
labels: tensor containing labels of a corresponding image.

How to use Caltech 101 Dataset with PyTorch and TensorFlow in Python

Train a model on Caltech 101 dataset with PyTorch in Python

Let’s use Hub’s built-in PyTorch one-line dataloader to connect the data to the compute:

				
					dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)

Train a model on Caltech 101 dataset with TensorFlow in Python

				
					dataloader = ds.tensorflow()

Additional Information about STN-PLAD Dataset

Caltech 101 Dataset Description

Homepage: http://www.vision.caltech.edu/datasets/

Caltech 101 Dataset Licensing Information

Hub users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.

If you’re a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!

Caltech 101 Dataset Citation Information

				
					@inproceedings{fei2004learning,
  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},
  booktitle={2004 conference on computer vision and pattern recognition workshop},
  pages={178--178},
  year={2004},
  organization={IEEE}
}

Caltech 101 Dataset FAQs

What is the Caltech 101 dataset for Python?

The Caltech-101 dataset comprises images of objects belonging to 101 classes, plus one background clutter class. Each image has labeled with a single object. Each class contains roughly 40 to 800 images, totaling around 9k images. Images are of variable sizes, with typical edge lengths of 200-300 pixels.

What is the Caltech 101 dataset used for?

The Caltech 101 dataset is commonly used to train and test computer vision recognition and classification algorithms. Using the Caltech 101 dataset comes with several advantages over other similar datasets as almost all the images within each category are uniform in image size. Caltech 101 also contains detailed image annotations.

How to download the Caltech 101 dataset in Python?

You can load the Caltech 101 dataset quickly with one line of code using Activeloop Deep Lake the open-source package made in Python. Check out detailed instructions on how to load the Caltech 101 dataset subset in Python.

How can I use Caltech 101 dataset in PyTorch or TensorFlow?

You can train a model on the Caltech 101 dataset with PyTorch in Python or train a model on Caltech 101 dataset with TensorFlow in Python. You can stream the Caltech 101 dataset while training a model in PyTorch or TensorFlow with one line of code using the open-source package Activeloop Deep Lake in Python.