Skip to content

Dataset · microsoft

Cats and dogs classification images

microsoft/cats_vs_dogs

A collection of cat and dog images from a Kaggle competition for binary classification.

What's inside

The dataset contains cat and dog images; 1,738 corrupted files were removed. This is part of a closed Kaggle competition and a subset of the Asirra dataset created for CAPTCHA tasks. Modality is images, metadata language is English, size is 10K-100K.

What you can do with it

  • Training CNN/ViT for binary classification
  • Testing augmentations and model robustness
  • Baseline for courses and experiments
Tasks
Image classification
Languages
English
Size
10K–100K rows
Downloads this month
7.2K
Likes
80

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("microsoft/cats_vs_dogs")