vandit15/Class-balanced-loss-pytorch

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

/ 100

Emerging

This helps deep learning engineers train image classification models more effectively when some categories have far fewer examples than others. It takes your model's predictions and the true labels, then applies a specialized loss function during training. This results in a more balanced model that performs better across all classes, especially the rare ones. It's for machine learning practitioners building and training computer vision models.

806 stars. No commits in the last 6 months.

Use this if you are training deep learning models on image datasets where the number of images varies greatly between different classes (e.g., many pictures of cats, few of lynx).

Not ideal if your dataset has an equal or near-equal number of samples for all classes, or if you are not working with deep learning image classification.

image-classification imbalanced-data deep-learning-training computer-vision machine-learning-engineering

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 22 / 25

How are scores calculated?

Stars

806

Forks

123

Language

Python

License

MIT

Compare

Class-balanced-loss-pytorch and class-balanced-loss

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"

Explore ML Frameworks

All categories Trending ML Framework directory Insights