Georgia Gkioxari 29cd181a83 CPU implem for face areas normals
Summary:
Added cpu implementation for face areas normals. Moved test and bm to separate functions.

```
Benchmark                                   Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
FACE_AREAS_NORMALS_2_100_300_False                196             268           2550
FACE_AREAS_NORMALS_2_100_300_True                 106             179           4733
FACE_AREAS_NORMALS_2_100_3000_False              1447            1630            346
FACE_AREAS_NORMALS_2_100_3000_True                107             178           4674
FACE_AREAS_NORMALS_2_1000_300_False               201             309           2486
FACE_AREAS_NORMALS_2_1000_300_True                107             186           4673
FACE_AREAS_NORMALS_2_1000_3000_False             1451            1636            345
FACE_AREAS_NORMALS_2_1000_3000_True               107             186           4655
FACE_AREAS_NORMALS_10_100_300_False               767             918            653
FACE_AREAS_NORMALS_10_100_300_True                106             167           4712
FACE_AREAS_NORMALS_10_100_3000_False             7036            7754             72
FACE_AREAS_NORMALS_10_100_3000_True               113             164           4445
FACE_AREAS_NORMALS_10_1000_300_False              748             947            669
FACE_AREAS_NORMALS_10_1000_300_True               108             169           4638
FACE_AREAS_NORMALS_10_1000_3000_False            7069            7783             71
FACE_AREAS_NORMALS_10_1000_3000_True              108             172           4646
FACE_AREAS_NORMALS_32_100_300_False              2286            2496            219
FACE_AREAS_NORMALS_32_100_300_True                108             180           4631
FACE_AREAS_NORMALS_32_100_3000_False            23184           24369             22
FACE_AREAS_NORMALS_32_100_3000_True               159             213           3147
FACE_AREAS_NORMALS_32_1000_300_False             2414            2645            208
FACE_AREAS_NORMALS_32_1000_300_True               112             197           4480
FACE_AREAS_NORMALS_32_1000_3000_False           21687           22964             24
FACE_AREAS_NORMALS_32_1000_3000_True              141             211           3540
--------------------------------------------------------------------------------

Benchmark                                         Avg Time(μs)      Peak Time(μs) Iterations
--------------------------------------------------------------------------------
FACE_AREAS_NORMALS_TORCH_2_100_300_False               5465            5782             92
FACE_AREAS_NORMALS_TORCH_2_100_300_True                1198            1351            418
FACE_AREAS_NORMALS_TORCH_2_100_3000_False             48228           48869             11
FACE_AREAS_NORMALS_TORCH_2_100_3000_True               1186            1304            422
FACE_AREAS_NORMALS_TORCH_2_1000_300_False              5556            6097             90
FACE_AREAS_NORMALS_TORCH_2_1000_300_True               1200            1328            417
FACE_AREAS_NORMALS_TORCH_2_1000_3000_False            48683           50016             11
FACE_AREAS_NORMALS_TORCH_2_1000_3000_True              1185            1306            422
FACE_AREAS_NORMALS_TORCH_10_100_300_False             24215           25097             21
FACE_AREAS_NORMALS_TORCH_10_100_300_True               1150            1314            435
FACE_AREAS_NORMALS_TORCH_10_100_3000_False           232605          234952              3
FACE_AREAS_NORMALS_TORCH_10_100_3000_True              1193            1314            420
FACE_AREAS_NORMALS_TORCH_10_1000_300_False            24912           25343             21
FACE_AREAS_NORMALS_TORCH_10_1000_300_True              1216            1330            412
FACE_AREAS_NORMALS_TORCH_10_1000_3000_False          239907          241253              3
FACE_AREAS_NORMALS_TORCH_10_1000_3000_True             1226            1333            408
FACE_AREAS_NORMALS_TORCH_32_100_300_False             73991           75776              7
FACE_AREAS_NORMALS_TORCH_32_100_300_True               1193            1339            420
FACE_AREAS_NORMALS_TORCH_32_100_3000_False           728932          728932              1
FACE_AREAS_NORMALS_TORCH_32_100_3000_True              1186            1359            422
FACE_AREAS_NORMALS_TORCH_32_1000_300_False            76385           79129              7
FACE_AREAS_NORMALS_TORCH_32_1000_300_True              1165            1310            430
FACE_AREAS_NORMALS_TORCH_32_1000_3000_False          753276          753276              1
FACE_AREAS_NORMALS_TORCH_32_1000_3000_True             1205            1340            415
--------------------------------------------------------------------------------
```

Reviewed By: bottler, jcjohnson

Differential Revision: D19864385

fbshipit-source-id: 3a87ae41a8e3ab5560febcb94961798f2e09dfb8
2020-02-13 11:42:48 -08:00
2020-01-23 11:53:46 -08:00
2020-01-23 11:53:46 -08:00
2020-01-23 11:53:46 -08:00
2020-01-31 14:31:00 -08:00
2020-02-05 09:50:52 -08:00
2020-02-13 11:42:48 -08:00
2020-01-23 11:53:46 -08:00
2020-01-23 11:53:46 -08:00
2020-02-04 17:27:16 -08:00
2020-02-07 09:56:59 -08:00
2020-01-23 11:53:46 -08:00
2020-01-24 07:19:21 -08:00
2020-01-23 11:53:46 -08:00

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%