Metadata-Version: 2.1
Name: sunds
Version: 0.4.1
Summary: Datasets for scene understanding and neural rendering.
Keywords: datasets,scene-understanding,neural rendering,nerf
Author-email: Sunds team <sunds@google.com>
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Dist: absl-py
Requires-Dist: etils[epath-no-tf,etqdm]
Requires-Dist: numpy>=1.17
Requires-Dist: tensorflow_datasets>=4.4
Requires-Dist: typing_extensions
Requires-Dist: pytest>=3.4 ; extra == "dev"
Requires-Dist: pytest-xdist ; extra == "dev"
Requires-Dist: pillow ; extra == "dev"
Project-URL: homepage, https://github.com/google-research/sunds
Project-URL: repository, https://github.com/google-research/sunds
Provides-Extra: dev

# Scene understanding datasets

[![Unittests](https://github.com/google-research/sunds/actions/workflows/pytest.yml/badge.svg)](https://github.com/google-research/sunds/actions/workflows/pytest.yml)
[![PyPI version](https://badge.fury.io/py/sunds.svg)](https://badge.fury.io/py/sunds)

SunDs is a collection of ready-to-use datasets for scene understanding tasks (3d
object detection, semantic segmentation, nerf rendering,...). It provides:

*   An API to easily load datasets to feed into your ML models.
*   A collection of ready-to-use datasets.
*   Helper tools to create new datasets.

```python
import sunds

ds = sunds.load('nerf_synthetic/lego', split='train', task=sunds.task.Nerf())
for ex in ds:
  ex['ray_origin']
```

To use sunds, see the documentation:

*  [Intro guide](https://github.com/google-research/sunds/blob/master/docs/intro.md)
*  [Nerf guide](https://github.com/google-research/sunds/blob/master/docs/nerf.md)

*This is not an official Google product.*

