Official adversarial mixup resynthesis repository
-
Updated
Feb 14, 2020 - Python
Official adversarial mixup resynthesis repository
Japanese Handwritten Character Recognition using DropBlock Regulzarization
Hands-on tutorial on Bayesian optimization for learning rate optimization on the K-MNIST dataset using PyTorch.
Kuzushiji, a form of cursive writing that is popularized in pre-modern Japan prior to the 19th century. Most historical documents that exist today are written in this form of writing. Therefore, I wish to train a model that could transcribe ancient Kuzushiji scripts into modern characters for researchers.
Training a convolutional neural network on the KMNIST dataset
Translator from KMNIST encoded pages to readable EMNIST, based on unsupervised learning algorithms.
Add a description, image, and links to the kmnist topic page so that developers can more easily learn about it.
To associate your repository with the kmnist topic, visit your repo's landing page and select "manage topics."