Some  visual recognition datasets have set benchmarks for supervised learning (Caltech101, Caltech256, CaltechBirds, CIFAR-10 andCIFAR-100) and unsupervised or self-taught learning algorithms(STL10) using  deep learning across different object categories for various researches and developments. Under visual recognition mainly comes image classification, image segmentation and localization,  object detection and various other use case problems. Many of these datasets have APIs present across some deep learning frameworks. I’ll be mentioning some of them in this article which can be directly imported and used to train models.

Cifar(Canadian Institute of Advanced Research) is a subset of  80 million tiny images dataset which has been collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton.

Dataset can be found on the official website of the  Computer Science department of the University of Toronto.

California Institute of Technology( Caltech) – a private research institute. Caltech vision databases are present under the  Computational Vision section.

STL10 dataset was inspired byCIFAR-10, the dataset is present in the official website of the computer science department, Stanford University.

Taking our visual recognition datasets discussions further, today we will be talking about these datasets features along with some python code snippets on how to use them.


#python #pytorch #stl10 #tensorflow #visual recognition

Guide to Visual Recognition Datasets for Deep Learning with Python Code
20.40 GEEK