Command Palette
Search for a command to run...
Luke N. Darlow; Elliot J. Crowley; Antreas Antoniou; Amos J. Storkey
Abstract
In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10. It was compiled by combining CIFAR-10 with images selected and downsampled from the ImageNet database. We present the approach to compiling the dataset, illustrate the example images for different classes, give pixel distributions for each part of the repository, and give some standard benchmarks for well known models. Details for download, usage, and compilation can be found in the associated github repository.
Code Repositories
BayesWatch/cinic-10
Official
pytorch
Mentioned in GitHub
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| image-classification-on-cinic-10 | ResNeXt29_2x64d | Accuracy: 91.45 |
| image-classification-on-cinic-10 | ResNet-18 | Accuracy: 90.27 |
| image-classification-on-cinic-10 | VGG-16 | Accuracy: 87.77 |
| image-classification-on-cinic-10 | DenseNet-121 | Accuracy: 91.26 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp