orientloss

PyPI page
Home page
Author: None
Summary: orientLoss is a classification loss function @pytorch. It less prone to overfitting compared to crossEntropy. Compatible with random vector/embeddings with direction-indicating categories、probabilistic、oneHot as target.
Latest version: 0.0.8
Required dependencies: torch

Downloads last day: 10
Downloads last week: 31
Downloads last month: 40