| Name | Version | Summary | date |
| orientLoss |
0.0.2 |
orientLoss is a classification loss function @pytorch. It less prone to overfitting compared to crossEntropy. Compatible with random vector/embeddings with direction-indicating categoriesăprobabilisticăoneHot as target. |
2025-07-30 17:18:02 |
| fftLoss |
0.0.1 |
The fftLoss @PyTorch is a frequency domain loss function that prevents the problem of weak frequency components being suppressed by strong frequency components when using a regular loss function. |
2025-07-30 13:41:24 |
| sysloss |
1.10.0 |
Power tree analysis of circuits, boards and systems. |
2025-01-19 10:31:45 |
| balanced-loss |
0.1.1 |
Easy to use class-balanced cross-entropy and focal loss implementation for Pytorch. |
2024-12-16 18:59:18 |
| mmcr |
0.1.0 |
MMCR Loss: Learning efficient coding of natural images with maximum manifold capacity representations |
2024-09-16 08:18:10 |
| tf-seq2seq-losses |
0.3.0 |
Tensorflow implementations for (CTC) loss functions that are fast and support second-order derivatives. |
2024-06-20 20:41:32 |