Loss Python Packages

oasislmf

Loss modelling framework.

zclip

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

focal-frequency-loss

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

llama

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

pyincore

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.

seqmetrics

Various errors for tabular/structured/time-series data

starttf

A tensorflow batteries included kit to write tensorflow networks from scratch or use existing ones.

sysloss

Power tree analysis of circuits, boards and systems.

orientloss

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.

beta-divergence-metrics

PyTorch implementations of the beta divergence loss.

nebula-loss

1 Loss Function For Everything

paddle-msssim

Fast and differentiable MS-SSIM and SSIM for Paddle.

tf-focal-frequency-loss

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

deepevolution

Deepevolution is a PIP package for evolving tensorflow keras models with a genetic algorithm towards fitting a fitness function.

treeboost-autograd

Easy Custom Losses for Tree Boosters using Pytorch

deep-plots

📉 Visualize your Deep Learning training in static graphics

fftloss

The fftLoss @PyTorch is a frequency domain loss function that prevents the problem of weak frequency components being suppressed by strong frequency components when using a regular loss function.

torchextractx

A PyTorch context manager that lets nested nn.Module objects register auxiliary losses, metrics, hooks, and intermediate outputs via add_loss() / add_metric() — then collects them in the training step, so you don't need to modify forward() signatures just to pass data up the call chain.

idsim

This repository can help researchers who want to use face recognition in their research.