Loss Functions Python Packages

auraloss

Collection of audio-focused loss functions in PyTorch

185K 864 78

pytorch-optimizer

optimizer & lr scheduler & loss function collections in PyTorch

178K 412 38

dists-pytorch

IQA: Deep Image Structure and Texture Similarity Metric

84K 478 46

focal-loss

TensorFlow implementation of focal loss

23K 191 42

torch-log-wmse

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

3K 46 1

torch-l1-snr

Variations of L1 SNR Loss function for training audio source separation machine learning models

2K 43 0

torch-log-wmse-audio-quality

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

1K 46 1

bokbokbok

Custom Losses and Metrics for XGBoost, LightGBM

974 39 7

iqa-pytorch

Comparison of IQA models in Perceptual Optimization

964 322 42

pytorch-focalloss

PyTorch implementation of binary and multi-class focal loss functions

917 1 0

balanced-loss

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

806 98 9

pylandscape

This project propose the loss landscape analysis as effective methodology to understand the robustness against natural perturbation of QNN.

457 3 1

mtl-uncertainty-loss

PyTorch unofficial implementation for uncertainty-weighted multi-task loss (Kendall et al., 2018)

385 0 0

gedml

GeDML is an easy-to-use generalized deep metric learning library, which contains state-of-the-art deep metric learning algorithms and auxiliary modules to build end-to-end compute vision systems

349 36 3

comport-ai

An HR predictive analytics tool that forecasts the likely range of a worker’s future job performance, using ANNs whose custom loss functions enable them to formulate prediction intervals that are as small as possible, while being just large enough to contain a worker’s actual future performance in most cases.

249 2 0