CoinCheung/pytorch-loss
Collection of PyTorch loss functions and CUDA-accelerated operators for training deep learning models.
Not currently ranked — collecting fresh signals.
star history
This repository provides PyTorch implementations of various loss functions used in deep learning training, including label smoothing, AMSoftmax, focal loss, triplet loss, dice loss, and IoU-based losses (GIOU/DIOU/CIOU). It also includes activation functions (Swish, Mish), one-hot encoding utilities with CUDA support, exponential moving average operators, and convolution variants like CoordConv and DynamicConvolution. Some operators are implemented as CUDA extensions requiring compilation.
Frequently asked
- What is CoinCheung/pytorch-loss?
- Collection of PyTorch loss functions and CUDA-accelerated operators for training deep learning models.
- Is pytorch-loss open source?
- Yes — CoinCheung/pytorch-loss is open source, released under the MIT license.
- What language is pytorch-loss written in?
- CoinCheung/pytorch-loss is primarily written in Python.
- How popular is pytorch-loss?
- CoinCheung/pytorch-loss has 2.3k stars on GitHub.
- Where can I find pytorch-loss?
- CoinCheung/pytorch-loss is on GitHub at https://github.com/CoinCheung/pytorch-loss.