- 18 Oct, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: Keep using at:: instead of torch:: so we don't need torch/extension.h and can keep other compilers happy. Reviewed By: patricklabatut Differential Revision: D31688436 fbshipit-source-id: 1825503da0104acaf1558d17300c02ef663bf538
-
Jeremy Reizenstein authored
Summary: Few tweaks to make CUDA build on windows happier, as remarked in #876. Reviewed By: patricklabatut Differential Revision: D31688188 fbshipit-source-id: 20816d6215f2e3ec898f81ae4221b1c2ff24b64f
-
- 17 Oct, 2021 1 commit
-
-
Ignacio Rocco authored
Summary: - Added clarifications about NDC coordinate system for square and non-square images. Pull Request resolved: https://github.com/fairinternal/pytorch3d/pull/28 Reviewed By: nikhilaravi Differential Revision: D31681444 Pulled By: bottler fbshipit-source-id: f71eabe9b3dd54b9372cef617e08f837f316555b
-
- 16 Oct, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: Small docs fixes: spelling. Avoid things which get out of date quickly: year, version. Reviewed By: patricklabatut Differential Revision: D31659927 fbshipit-source-id: b0111140bdaf3c6cadc09f70621bf5656909ca02
-
Jeremy Reizenstein authored
Summary: Fix #873, that grid_sizes defaults to the wrong dtype in points2volumes code, and mask doesn't have a proper default. Reviewed By: nikhilaravi Differential Revision: D31503545 fbshipit-source-id: fa32a1a6074fc7ac7bdb362edfb5e5839866a472
-
- 13 Oct, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: Make eps=1e-4 by default for coplanar check and also enable it to be set by the user in call to `box3d_overlap`. Reviewed By: gkioxari Differential Revision: D31596836 fbshipit-source-id: b57fe603fd136cfa58fddf836922706d44fe894e
-
- 11 Oct, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: PyTorch 1.6.0 came out on 28 Jul 2020. Stop builds for 1.5.0 and 1.5.1. Also update the news section of the README for recent releases. Reviewed By: nikhilaravi Differential Revision: D31442830 fbshipit-source-id: 20bdd8a07090776d0461240e71c6536d874615f6
-
- 08 Oct, 2021 2 commits
-
-
Pyre Bot Jr authoredDifferential Revision: D31496551 fbshipit-source-id: 705fd88f319875db3f7938a2946c48a51ea225f5
-
Nikhila Ravi authored
Summary: The epsilon value is important for determining whether vertices are inside/outside a plane. Reviewed By: gkioxari Differential Revision: D31485247 fbshipit-source-id: 5517575de7c02f1afa277d00e0190a81f44f5761
-
- 07 Oct, 2021 4 commits
-
-
Jeremy Reizenstein authored
Summary: Increase some test tolerances so that they pass in more situations, and re-enable two tests. Reviewed By: nikhilaravi Differential Revision: D31379717 fbshipit-source-id: 06a25470cc7b6d71cd639d9fd7df500d4b84c079
-
Ruilong Li authored
Summary: For non square image, the NDC space in pytorch3d is not square [-1, 1]. Instead, it is [-1, 1] for the smallest side, and [-u, u] for the largest side, where u > 1. This behavior is followed by the pytorch3d renderer. See the function `get_ndc_to_screen_transform` for a example. Without this fix, the rendering result is not correct using the converted pytorch3d-camera from a opencv-camera on non square images. This fix also helps the `transform_points_screen` function delivers consistent results with opencv projection for the converted pytorch3d-camera. Reviewed By: classner Differential Revision: D31366775 fbshipit-source-id: 8858ae7b5cf5c0a4af5a2af40a1358b2fe4cf74b
-
CodemodService Bot authored
Reviewed By: zertosh Differential Revision: D31464988 fbshipit-source-id: 2eaf28d6869ccb70fd4df4f7de15d959cdaba0be
-
Jeremy Reizenstein authored
Summary: Do the website building in a docker container to avoid worrying about dependencies. Reviewed By: nikhilaravi Differential Revision: D30223892 fbshipit-source-id: 77b7b4630188167316891381f6ca9e9fbe7f0a05
-
- 06 Oct, 2021 1 commit
-
-
Nikita Smetanin authored
Summary: Symmetric eigenvalues 3x3 implementation from https://github.com/fairinternal/denseposeslim/blob/roman_c3dpo/tools/functions.py#L612 based on https://en.wikipedia.org/wiki/Eigenvalue_algorithm#3.C3.973_matrices and https://www.geometrictools.com/Documentation/RobustEigenSymmetric3x3.pdf Benchmarks show significant outperformance of symeig3x3 in comparison with torch implementations (torch.symeig and torch.linalg.eigh) on GPU (P100), especially for large batches: 70-280ns per sample vs 3400ns per sample for torch_linalg_eigh_1048576_cpu It's worth mentioning that torch.linalg.eigh is still comparably fast for batches up to 8192 on CPU. Some tests are still failing as the error thresholds need to be adjusted appropriately. Reviewed By: patricklabatut Differential Revision: D29915453 fbshipit-source-id: 7c1b062da631c57c4e22a42dd0027ea5e205f1b5
-
- 05 Oct, 2021 2 commits
-
-
Jeremy Reizenstein authored
Summary: update Reviewed By: patricklabatut Differential Revision: D31338002 fbshipit-source-id: 90ed6c2ea411c0384dd233ee88e51b5f608eef88
-
Jeremy Reizenstein authored
Summary: now supporting PyTorch 1.9.1 Reviewed By: patricklabatut Differential Revision: D31338001 fbshipit-source-id: 11140819d10af388d31905a39f1da136cf9c5ff2
-
- 04 Oct, 2021 1 commit
-
-
Georgia Gkioxari authored
Summary: A small fix for the iou3d note Reviewed By: bottler Differential Revision: D31370686 fbshipit-source-id: 6c97302b5c78de52915f31be70f234179c4b246d
-
- 02 Oct, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: New function to randomly subsample Pointclouds to a maximum size. Reviewed By: nikhilaravi Differential Revision: D30936533 fbshipit-source-id: 789eb5004b6a233034ec1c500f20f2d507a303ff
-
- 01 Oct, 2021 3 commits
-
-
Jeremy Reizenstein authored
Summary: Move the core of add_points_to_volumes to the new C++/CUDA implementation. Add new flag to let the user stop this happening. Avoids copies. About a 30% speedup on the larger cases, up to 50% on the smaller cases. New timings ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000 4575 12591 110 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000 25468 29186 20 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000 202085 209897 3 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000 46059 48188 11 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000 83759 95669 7 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000 326056 339393 2 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000 2379 4738 211 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000 12100 63099 42 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000 63323 63737 8 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000 45216 45479 12 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000 57205 58524 9 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000 139499 139926 4 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000 40129 40431 13 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000 204949 239293 3 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000 1664541 1664541 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000 391573 395108 2 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000 674869 674869 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000 2713632 2713632 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000 12726 13506 40 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000 73103 73299 7 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000 598634 598634 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000 398742 399256 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000 543129 543129 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000 1242956 1242956 1 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000 1814 8884 276 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000 1996 8851 251 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000 4608 11529 109 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000 5183 12508 97 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000 7106 14077 71 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000 25914 31818 20 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000 1778 8823 282 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000 1825 8613 274 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000 3154 10161 159 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000 4888 9404 103 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000 5194 9963 97 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000 8109 14933 62 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000 3320 10306 151 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000 7003 8595 72 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000 49140 52957 11 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000 35890 36918 14 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000 58890 59337 9 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000 286878 287600 2 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000 2484 8805 202 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000 3967 9090 127 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000 19423 19799 26 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000 33228 33329 16 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000 37292 37370 14 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000 73550 74017 7 -------------------------------------------------------------------------------- ``` Previous timings ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_1000 10100 46422 50 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_10000 28442 32100 18 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[25, 25, 25]_100000 241127 254269 3 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_1000 54149 79480 10 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_10000 125459 212734 4 ADD_POINTS_TO_VOLUMES_cpu_10_trilinear_[101, 111, 121]_100000 512739 512739 1 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_1000 2866 13365 175 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_10000 7026 12604 72 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[25, 25, 25]_100000 48822 55607 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_1000 38098 38576 14 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_10000 48006 54120 11 ADD_POINTS_TO_VOLUMES_cpu_10_nearest_[101, 111, 121]_100000 131563 138536 4 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_1000 64615 91735 8 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_10000 228815 246095 3 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[25, 25, 25]_100000 3086615 3086615 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_1000 464298 465292 2 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_10000 1053440 1053440 1 ADD_POINTS_TO_VOLUMES_cpu_100_trilinear_[101, 111, 121]_100000 6736236 6736236 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_1000 11940 12440 42 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_10000 56641 58051 9 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[25, 25, 25]_100000 711492 711492 1 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_1000 326437 329846 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_10000 418514 427911 2 ADD_POINTS_TO_VOLUMES_cpu_100_nearest_[101, 111, 121]_100000 1524285 1524285 1 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_1000 5949 13602 85 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_10000 5817 13001 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[25, 25, 25]_100000 23833 25971 21 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_1000 9029 16178 56 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_10000 11595 18601 44 ADD_POINTS_TO_VOLUMES_cuda:0_10_trilinear_[101, 111, 121]_100000 46986 47344 11 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_1000 2554 9747 196 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_10000 2676 9537 187 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[25, 25, 25]_100000 6567 14179 77 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_1000 5840 12811 86 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_10000 6102 13128 82 ADD_POINTS_TO_VOLUMES_cuda:0_10_nearest_[101, 111, 121]_100000 11945 11995 42 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_1000 7642 13671 66 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_10000 25190 25260 20 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[25, 25, 25]_100000 212018 212134 3 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_1000 40421 45692 13 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_10000 92078 92132 6 ADD_POINTS_TO_VOLUMES_cuda:0_100_trilinear_[101, 111, 121]_100000 457211 457229 2 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_1000 3574 10377 140 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_10000 7222 13023 70 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[25, 25, 25]_100000 48127 48165 11 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_1000 34732 35295 15 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_10000 43050 51064 12 ADD_POINTS_TO_VOLUMES_cuda:0_100_nearest_[101, 111, 121]_100000 106028 106058 5 -------------------------------------------------------------------------------- ``` Reviewed By: nikhilaravi Differential Revision: D29548609 fbshipit-source-id: 7026e832ea299145c3f6b55687f3c1601294f5c0
-
Jeremy Reizenstein authored
Summary: Added CUDA implementation to match the new, still unused, C++ function for the core of points2vols. Reviewed By: nikhilaravi Differential Revision: D29548608 fbshipit-source-id: 16ebb61787fcb4c70461f9215a86ad5f97aecb4e
-
Jeremy Reizenstein authored
Summary: Single C++ function for the core of points2vols, not used anywhere yet. Added ability to control align_corners and the weight of each point, which may be useful later. Reviewed By: nikhilaravi Differential Revision: D29548607 fbshipit-source-id: a5cda7ec2c14836624e7dfe744c4bbb3f3d3dfe2
-
- 30 Sep, 2021 9 commits
-
-
Jeremy Reizenstein authored
Summary: Statement about compatibility. Reviewed By: nikhilaravi Differential Revision: D30697072 fbshipit-source-id: aeb5e3e0a08c1797033d8c00b24484c8a699cb02
-
Jeremy Reizenstein authored
Summary: Fix some missing or misplaced argument descriptions. Reviewed By: nikhilaravi Differential Revision: D31305132 fbshipit-source-id: af4fcee9766682b2b7f7f16327e839090e377be2
-
Simon Moisselin authored
Summary: y_lengths is about `y`, not `x`. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/862 Reviewed By: bottler Differential Revision: D31304434 Pulled By: patricklabatut fbshipit-source-id: 1db4cd57677fc018c229e02172f95ffa903d75eb
-
Theo-Cheynel authored
Summary: Changed mistake in Python f-strings causing an additional letter "f" to appear in the error messages. The error messages would read something like : ``` raise ValueError(f"Invalid rotation matrix shape f{matrix.shape}.") ValueError: Invalid rotation matrix shape ftorch.Size([4, 4]). ``` (with an additional f, probably a mistake) Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/851 Reviewed By: nikhilaravi Differential Revision: D31238831 Pulled By: patricklabatut fbshipit-source-id: 0ba3e61e488e467e997954278097889be606d4f8 -
Jeremy Reizenstein authored
Reviewed By: nikhilaravi Differential Revision: D31289856 fbshipit-source-id: 5a522a69537a873bacacf2a178e5f30771aef35f
-
Jeremy Reizenstein authored
Summary: Allow saving colors as 8bit when writing .ply files. Reviewed By: patricklabatut, nikitos9000 Differential Revision: D30905312 fbshipit-source-id: 44500982c9ed6d6ee901e04f9623e22792a0e7f7
-
Georgia Gkioxari authored
Summary: A note for our new algorithm for IoU of oriented 3D boxes. It includes * A description of the algorithm * A comparison with Objectron Reviewed By: nikhilaravi Differential Revision: D31288066 fbshipit-source-id: 0ea8da887bc5810bf4a3e0848223dd3590df1538
-
Nikhila Ravi authored
Summary: CUDA implementation of 3D bounding box overlap calculation. Reviewed By: gkioxari Differential Revision: D31157919 fbshipit-source-id: 5dc89805d01fef2d6779f00a33226131e39c43ed
-
Nikhila Ravi authored
Summary: C++ Implementation of algorithm to compute 3D bounding boxes for batches of bboxes of shape (N, 8, 3) and (M, 8, 3). Reviewed By: gkioxari Differential Revision: D30905190 fbshipit-source-id: 02e2cf025cd4fa3ff706ce5cf9b82c0fb5443f96
-
- 29 Sep, 2021 2 commits
-
-
Nikhila Ravi authored
Summary: I have implemented an exact solution for 3D IoU of oriented 3D boxes. This file includes: * box3d_overlap: which computes the exact IoU of box1 and box2 * box3d_overlap_sampling: which computes an approximate IoU of box1 and box2 by sampling points within the boxes Note that both implementations currently do not support batching. Our exact IoU implementation is based on the fact that the intersecting shape of the two 3D boxes will be formed by segments of the surface of the boxes. Our algorithm computes these segments by reasoning whether triangles of one box are within the second box and vice versa. We deal with intersecting triangles by clipping them. Reviewed By: gkioxari Differential Revision: D30667497 fbshipit-source-id: 2f747f410f90b7f854eeaf3036794bc3ac982917
-
Pyre Bot Jr authored
Differential Revision: D31266959 fbshipit-source-id: 878a59ca2cfe1389e42fc338653e8d3314b56b91
-
- 27 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Add conda builds for the newly released PyTorch version 1.9.1. Reviewed By: patricklabatut Differential Revision: D31140206 fbshipit-source-id: 697549a3ef0db8248f4f9b5c00cf1407296b5022
-
- 24 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Copy some descriptions of renderer parameters to more places so they are easier to find. Also a couple of small corrections, and make RasterizationSettings a dataclass. Reviewed By: nikhilaravi, patricklabatut Differential Revision: D30899822 fbshipit-source-id: 805cf366acb7d51cb308fa574deff0657c199673
-
- 23 Sep, 2021 1 commit
-
-
Jeremy Reizenstein authored
Summary: Attempt to fix #659, an observation that the rasterizer is nondeterministic, by resolving tied faces by picking those with lower index. Reviewed By: nikhilaravi, patricklabatut Differential Revision: D30699039 fbshipit-source-id: 39ed797eb7e9ce7370ae71259ad6b757f9449923
-
- 22 Sep, 2021 3 commits
-
-
Jeremy Reizenstein authored
Summary: Unlike other cu files, sigmoid_alpha_blend uses torch/extension.h. Avoid for possible build speed win and because of a reported problem #843 on windows with CUDA 11.4. Reviewed By: nikhilaravi Differential Revision: D31054121 fbshipit-source-id: 53a1f985a1695a044dfd2ee1a5b0adabdf280595
-
Jeremy Reizenstein authored
Summary: Rename sample_farthest_point.cpp to not match its CUDA equivalent. Reviewed By: nikhilaravi Differential Revision: D31006645 fbshipit-source-id: 135b511cbde320d2b3e07fc5b027971ef9210aa9
-
Jeremy Reizenstein authored
Summary: Remove use of nonstandard C++. Noticed on windows in issue https://github.com/facebookresearch/pytorch3d/issues/843. (We use `__restrict__` in CUDA, where it is fine, even on windows) Reviewed By: nikhilaravi Differential Revision: D31006516 fbshipit-source-id: 929ba9b3216cb70fad3ffa3274c910618d83973f
-
- 18 Sep, 2021 1 commit
-
-
Pyre Bot Jr authored
Differential Revision: D31042748 fbshipit-source-id: fffb983bd6765d306a407587ddf64e68e57e9ecc
-
- 15 Sep, 2021 1 commit
-
-
Nikhila Ravi authored
Summary: CUDA implementation of farthest point sampling algorithm. ## Visual comparison Compared to random sampling, farthest point sampling gives better coverage of the shape. {F658631262} ## Reduction Parallelized block reduction to find the max value at each iteration happens as follows: 1. First split the points into two equal sized parts (e.g. for a list with 8 values): `[20, 27, 6, 8 | 11, 10, 2, 33]` 2. Use half of the thread (4 threads) to compare pairs of elements from each half (e.g elements [0, 4], [1, 5] etc) and store the result in the first half of the list: `[20, 27, 6, 33 | 11, 10, 2, 33]` Now we no longer care about the second part but again divide the first part into two `[20, 27 | 6, 33| -, -, -, -]` Now we can use 2 threads to compare the 4 elements 4. Finally we have gotten down to a single pair `[20 | 33 | -, - | -, -, -, -]` Use 1 thread to compare the remaining two elements 5. The max will now be at thread id = 0 `[33 | - | -, - | -, -, -, -]` The reduction will give the farthest point for the selected batch index at this iteration. Reviewed By: bottler, jcjohnson Differential Revision: D30401803 fbshipit-source-id: 525bd5ae27c4b13b501812cfe62306bb003827d2
-
