https://github.com/ttl/torchbp
Fast C++ Pytorch extension for differentiable synthetic aperture radar image formation and autofocus library on CPU and GPU
https://github.com/ttl/torchbp
radar rf synthetic-aperture-radar
Last synced: 3 months ago
JSON representation
Fast C++ Pytorch extension for differentiable synthetic aperture radar image formation and autofocus library on CPU and GPU
- Host: GitHub
- URL: https://github.com/ttl/torchbp
- Owner: Ttl
- License: mit
- Created: 2025-01-20T14:36:31.000Z (4 months ago)
- Default Branch: master
- Last Pushed: 2025-03-05T16:00:17.000Z (3 months ago)
- Last Synced: 2025-03-05T17:20:04.435Z (3 months ago)
- Topics: radar, rf, synthetic-aperture-radar
- Language: Cuda
- Homepage:
- Size: 50.8 KB
- Stars: 52
- Watchers: 5
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
- License: LICENSE
Awesome Lists containing this project
README
# Torchbp
Fast C++ Pytorch extension for differentiable synthetic aperture radar image formation and autofocus library on CPU and GPU.
Only Nvidia GPUs are supported. Currently, some operations are not supported on CPU.
On RTX 3090 Ti backprojection on polar grid achieves 225 billion backprojections/s.
## Installation
### From source
```bash
git clone https://github.com/Ttl/torchbp.git
cd torchbp
pip install .
```
## Documentation
API documentation and examples can be built with sphinx.
```bash
pip install .[docs]
cd docs
make html
```
Open `docs/build/html/index.html`.