Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

face recognition training project(pytorch)

遥感图像的语义分割，基于深度学习，在Tensorflow框架下，利用TF.Keras，运行环境TF2.0+

Ever wondered how to code your Neural Network using NumPy, with no frameworks involved?

Reproducing experimental results of LL4AL [Yoo et al. 2019 CVPR]

Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".

Loss modelling framework.

Prostate MR Image Segmentation 2012

YOLOv4 Pytorch implementation with all freebies and specials and 15+ more exclusive improvements. Easy to use!

Code for the paper "Facial Emotion Recognition: State of the Art Performance on FER2013"

Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.

Focal Loss of multi-classification in tensorflow

An implementation for mnist center loss training and visualization

Library for testing and measuring network loss and latency between distributed endpoints.

Deep Attentive Center Loss

Prostate MR Image Segmentation 2012

a simple pytorch implement of Multi-Sample Dropout

Weighted Focal Loss for multilabel classification

I very recently lost my amazing Mom to Pancreatic Cancer and this repository shares my story. I also will be writing stories about her and daily journal entries on how I'm feeling after the painful loss.

Implementation of "Anchor Loss: Modulating loss scale based on prediction difficulty"

Loss & LAtency MAtrix

Official implementation for paper "Relational Surrogate Loss Learning", ICLR 2022

Bootstrapping loss function implementation in pytorch

Easy Custom Losses for Tree Boosters using Pytorch

Code of the ICASSP 2022 paper "Gradient Variance Loss for Structure Enhanced Super-Resolution"

A loss function for categories with a hierarchical structure.

Implementation of related angular-margin-based classification loss functions for training (face) embedding models: SphereFace, CosFace, ArcFace and MagFace.

pyIncore is a component of IN-CORE. It is a python package consisting of two primary components: 1) a set of service classes to interact with the IN-CORE web services, and 2) IN-CORE analyses . The pyIncore allows users to apply various hazards to infrastructure in selected areas, propagating the effect of physical infrastructure damage and loss of functionality to social and economic impacts.