Georgia Gkioxari b2b0c5a442 knn autograd
Summary:
Adds knn backward to return `grad_pts1` and `grad_pts2`. Adds `knn_gather` to return the nearest neighbors in pts2.

The BM tests include backward pass and are ran on an M40.
```
Benchmark                               Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
KNN_SQUARE_32_256_128_3_24_cpu              39558           43485             13
KNN_SQUARE_32_256_128_3_24_cuda:0            1080            1404            463
KNN_SQUARE_32_256_512_3_24_cpu              81950           85781              7
KNN_SQUARE_32_256_512_3_24_cuda:0            1519            1641            330
--------------------------------------------------------------------------------

Benchmark                               Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
KNN_RAGGED_32_256_128_3_24_cpu              13798           14650             37
KNN_RAGGED_32_256_128_3_24_cuda:0            1576            1713            318
KNN_RAGGED_32_256_512_3_24_cpu              31255           32210             16
KNN_RAGGED_32_256_512_3_24_cuda:0            2024            2162            248
--------------------------------------------------------------------------------
```

Reviewed By: jcjohnson

Differential Revision: D20945556

fbshipit-source-id: a16f616029c6b5f8c2afceb5f2bc12c5c20d2f3c
2020-04-14 17:22:56 -07:00
2020-04-07 09:42:31 -07:00
2020-03-30 06:17:27 -07:00
2020-04-07 09:42:31 -07:00
2020-04-14 17:22:56 -07:00
2020-04-14 17:22:56 -07:00
2020-03-26 11:02:31 -07:00
2020-01-23 11:53:46 -08:00
2020-03-29 14:51:02 -07:00
2020-02-19 23:16:50 -08:00
2020-03-23 09:20:42 -07:00
2020-03-17 12:48:43 -07:00
2020-03-18 11:39:31 -07:00
2020-03-29 14:51:02 -07:00

CircleCI Anaconda-Server Badge

Introduction

PyTorch3D provides efficient, reusable components for 3D Computer Vision research with PyTorch.

Key features include:

  • Data structure for storing and manipulating triangle meshes
  • Efficient operations on triangle meshes (projective transformations, graph convolution, sampling, loss functions)
  • A differentiable mesh renderer

PyTorch3D is designed to integrate smoothly with deep learning methods for predicting and manipulating 3D data. For this reason, all operators in PyTorch3D:

  • Are implemented using PyTorch tensors
  • Can handle minibatches of hetereogenous data
  • Can be differentiated
  • Can utilize GPUs for acceleration

Within FAIR, PyTorch3D has been used to power research projects such as Mesh R-CNN.

Installation

For detailed instructions refer to INSTALL.md.

License

PyTorch3D is released under the BSD-3-Clause License.

Tutorials

Get started with PyTorch3D by trying one of the tutorial notebooks.

Deform a sphere mesh to dolphin Bundle adjustment
Render textured meshes Camera position optimization

Documentation

Learn more about the API by reading the PyTorch3D documentation.

We also have deep dive notes on several API components:

Development

We welcome new contributions to PyTorch3D and we will be actively maintaining this library! Please refer to CONTRIBUTING.md for full instructions on how to run the code, tests and linter, and submit your pull requests.

Contributors

PyTorch3D is written and maintained by the Facebook AI Research Computer Vision Team.

Citation

If you find PyTorch3D useful in your research, please cite:

@misc{ravi2020pytorch3d,
  author =       {Nikhila Ravi and Jeremy Reizenstein and David Novotny and Taylor Gordon
                  and Wan-Yen Lo and Justin Johnson and Georgia Gkioxari},
  title =        {PyTorch3D},
  howpublished = {\url{https://github.com/facebookresearch/pytorch3d}},
  year =         {2020}
}
Description
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Readme BSD-3-Clause 73 MiB
Languages
Python 80.9%
C++ 10.2%
Cuda 6.3%
C 0.9%
Shell 0.8%
Other 0.9%