https://github.com/rockerboo/wavelet-loss
Wavelet-based loss calculations
https://github.com/rockerboo/wavelet-loss
pytorch wavelet-transform wavelets
Last synced: 7 months ago
JSON representation
Wavelet-based loss calculations
- Host: GitHub
- URL: https://github.com/rockerboo/wavelet-loss
- Owner: rockerBOO
- Created: 2025-07-15T20:57:29.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-07-17T23:24:47.000Z (8 months ago)
- Last Synced: 2025-07-27T23:47:35.709Z (8 months ago)
- Topics: pytorch, wavelet-transform, wavelets
- Language: Python
- Homepage:
- Size: 178 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Wavelet Loss
A Python library for wavelet-based loss calculations in machine learning.
## Installation
```bash
pip install git+https://github.com/rockerBOO/wavelet-loss.git
```
## Usage
## Quick Start
```python
import torch
from wavelet_loss import WaveletLoss
# Create a loss function
loss_fn = WaveletLoss()
# Example usage in a training loop
prediction = torch.randn(10, 1)
target = torch.randn(10, 1)
loss = loss_fn(prediction, target)
```
## Features
- Discrete Wavelet Transform (DWT)
- Quadrature Wavelet Transform (QWT)
- Stationary Wavelet Transform (SWT)
- Wavelet-based loss calculations
## Development
- Run tests: `uv run pytest`
- Python 3.10+ required