pytorch-loss
Loss functions
Provides a comprehensive set of implementation of various loss functions and operators for deep learning models
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
2k stars
23 watching
374 forks
Language: Python
last commit: 4 months ago amsoftmaxcudadice-lossemafocal-losslabel-smoothinglovasz-softmaxmishpartial-fcpytorchtriplet-loss
Related projects:
| Repository | Description | Stars |
|---|---|---|
 hanxunh/active-passive-losses | A PyTorch-based framework for implementing normalized loss functions to improve deep learning model robustness against noisy labels. | 134 |
 alanchou/truncated-loss | An implementation of a loss function designed to improve the training of deep neural networks with noisy labels | 126 |
 mblondel/fenchel-young-losses | Provides Fenchel-Young losses for probabilistic classification in PyTorch/TensorFlow/scikit-learn. | 183 |
 bes-dev/mpl.pytorch | A PyTorch implementation of a loss function used in semantic image segmentation | 175 |
 kefirski/pytorch_neg_loss | A PyTorch implementation of negative sampling loss for text classification models | 125 |
 rachtsingh/lgamma | Implementations of mathematical special functions for use in machine learning and PyTorch applications | 24 |
 chosj95/mimo-unet | Develops a deep learning model for single image deblurring with improved performance and computational efficiency | 382 |
 kaiyangzhou/dassl.pytorch | A PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision. | 1,236 |
 pochih/fcn-pytorch | A Python implementation of fully convolutional networks for semantic segmentation in computer vision. | 409 |
 zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,044 |
 seannaren/warp-ctc | PyTorch bindings for the Warp-CTC loss function used in speech recognition. | 757 |
 unsky/focal-loss | An implementation of focal loss for dense object detection in mxnet. | 486 |
 yunlongdong/fcn-pytorch | A PyTorch implementation of FCN for semantic segmentation with an easy-to-use interface and pre-trained models. | 161 |
 zudi-lin/pytorch_connectomics | A deep learning framework for automatic and semi-automatic segmentation of 3D image stacks in connectomics | 172 |
 zapata-engineering/orqviz | Visualizes loss landscapes of parameterized quantum algorithms | 86 |