The HASYv2 dataset
arXiv:1701.08380
Abstract
This paper describes the HASYv2 dataset. HASY is a publicly available, free of charge dataset of single symbols similar to MNIST. It contains 168233 instances of 369 classes. HASY contains two challenges: A classification challenge with 10 pre-defined folds for 10-fold cross-validation and a verification challenge.
Cited by in corpus (6)
- Tunneling Neural Perception and Logic Reasoning through Abductive Learning
- Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
- Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
- Compressed DenseNet for Lightweight Character Recognition
- Effect of the initial configuration of weights on the training and function of artificial neural networks
- Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path