statmlben/ensLoss
EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
EnsLoss helps machine learning practitioners build more accurate classification models by combining different loss functions during training. It takes your prepared image or tabular dataset and model architecture, and outputs a classification model that is less prone to overfitting, achieving higher prediction accuracy. This is ideal for data scientists or ML engineers focused on robust classification performance.
Use this if you are struggling with overfitting in your binary classification models and want to achieve consistently higher accuracy across different datasets without manually searching for the best loss function.
Not ideal if your primary goal is multi-class or text classification, or if you require an extremely lightweight model where every computational step must be minimized.
Stars
34
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/statmlben/ensLoss"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HelmchenLabSoftware/Cascade
Calibrated inference of spiking from calcium ΔF/F data using deep networks
adobe/antialiased-cnns
pip install antialiased-cnns to improve stability and accuracy
KaiyangZhou/pytorch-center-loss
Pytorch implementation of Center Loss
kimhc6028/relational-networks
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)
devsisters/pointer-network-tensorflow
TensorFlow implementation of "Pointer Networks"