pytorch-loss
by CoinCheung
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
AI summary
Loss functions
Provides a comprehensive set of implementation of various loss functions and operators for deep learning models
- stars
- 2.2K
- forks
- 374
- watching
- 23
Similar projects
Found by comparing what the projects do, not just their names.
Loss function framework
A PyTorch-based framework for implementing normalized loss functions to improve deep learning model robustness against noisy labels.
Noisy label loss function
An implementation of a loss function designed to improve the training of deep neural networks with noisy labels
Loss functions
Provides Fenchel-Young losses for probabilistic classification in PyTorch/TensorFlow/scikit-learn.
Image Segmentation Loss
A PyTorch implementation of a loss function used in semantic image segmentation
Negative sampler
A PyTorch implementation of negative sampling loss for text classification models
Special function library
Implementations of mathematical special functions for use in machine learning and PyTorch applications
Deblurring model
Develops a deep learning model for single image deblurring with improved performance and computational efficiency
Computer Vision Toolkit
A PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision.
FCN
A Python implementation of fully convolutional networks for semantic segmentation in computer vision.
Deep learning toolkit
A Python framework for building deep learning models with optimized encoding layers and batch normalization.
Speech recognition library
PyTorch bindings for the Warp-CTC loss function used in speech recognition.
Object detector
An implementation of focal loss for dense object detection in mxnet.
Segmentation library
A PyTorch implementation of FCN for semantic segmentation with an easy-to-use interface and pre-trained models.
Connectomics toolkit
A deep learning framework for automatic and semi-automatic segmentation of 3D image stacks in connectomics
Loss landscape viewer
Visualizes loss landscapes of parameterized quantum algorithms
