loss-function 开源项目推荐（63 个）

bnu-wangxun /Deep_Metric

Deep Metric Learning

EndlessSora /focal-frequency-loss

[ICCV 2021]图像重建与合成中的焦频损耗

cvqluu /Angular-Penalty-Softmax-Losses-Pytorch

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)

keonlee9420 /Soft-DTW-Loss

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

lartpang /mssim.pytorch

A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.

nathanrooy /landscapes

A dependency free library of standardized optimization test functions written in pure Python.

xxxupeng /ADL

[CVPR 2024] Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

PerdonLiu /CSE-Autoloss

Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.

AdaSwarm /AdaSwarm

SwarmLoss: a PyTorch loss that trains through non-convex and non-differentiable objectives by fusing particle-swarm optimisation with gradient-based optimisers like Adam.

estija /Co-VeGAN

Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction

arhtur007 /Angular-Triplet-Center-Loss

Angular triplet center loss implementation in Pytorch.

rsy6318 /DDF-Loss

Directional Distance Field for Modeling the Difference between 3D Point Clouds

ashleyfhh /MS-SigNet

MultiScale Signature feature learning Network for offline handwritten signature verification

ZohebAbai /tf-focal-frequency-loss

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

Akinori-F-Ebihara /LLLR_toymodel

A simple 3-layer fully connected network performing the density ratio estimation using the loss for log-likelihood ratio estimation (LLLR).

masadcv /PROPEL

Official PyTorch implementation for "PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks"

ChenLiu-1996 /AdversarialFocalLoss

Adversarial Focal Loss: Asking Your Discriminator for Hard Examples.

cnicholas /processbehavior

Process behavior charts (control charts / SPC) for Python — XmR, Xbar-S, histograms, capability, Taguchi loss. Implements Bishop's Variance Analysis System with chart math validated against published reference results.

ZekiZeybek /TNML-surrogate-loss

Tensor-Network Machine Learning with Matrix Product States, trained via a surrogate (projective) loss instead of standard negative log-likelihood

gwr3n /pwlf-milp

Piecewise linear approximations for the static-dynamic uncertainty strategy in stochastic lot-sizing