- 24 Apr, 2020 3 commits
-
-
Michele Sanna authored
Summary: Signed-off-by:
Michele Sanna <sanna@arrival.com> fixes the bin_size calculation with a formula for any image_size > 64. Matches the values chosen so far. simple test: ``` import numpy as np import matplotlib.pyplot as plt image_size = np.arange(64, 2048) bin_size = np.where(image_size <= 64, 8, (2 ** np.maximum(np.ceil(np.log2(image_size)) - 4, 4)).astype(int)) print(image_size) print(bin_size) for ims, bins in zip(image_size, bin_size): if ims <= 64: assert bins == 8 elif ims <= 256: assert bins == 16 elif ims <= 512: assert bins == 32 elif ims <= 1024: assert bins == 64 elif ims <= 2048: assert bins == 128 assert (ims + bins - 1) // bins < 22 plt.plot(image_size, bin_size) plt.grid() plt.show() ```  Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/90 Reviewed By: jcjohnson Differential Revision: D21160372 Pulled By: nikhilaravi fbshipit-source-id: 660cf5832f4ca5be243c435a6bed969596fc0188
-
Nikhila Ravi authored
Summary: Updates to: - enable cuda kernel launches on any GPU (not just the default) - cuda and contiguous checks for all kernels - checks to ensure all tensors are on the same device - error reporting in the cuda kernels - cuda tests now run on a random device not just the default Reviewed By: jcjohnson, gkioxari Differential Revision: D21215280 fbshipit-source-id: 1bedc9fe6c35e9e920bdc4d78ed12865b1005519
-
Nikhila Ravi authored
Summary: Updated the load obj function to support creating of a per face texture map using the information in an .mtl file. Uses the approach from in SoftRasterizer. Currently I have ported in the SoftRasterizer code but this is only to help with comparison and will be deleted before landing. The ShapeNet Test data will also be deleted. Here is the [Design doc](https://docs.google.com/document/d/1AUcLP4QwVSqlfLAUfbjM9ic5vYn9P54Ha8QbcVXW2eI/edit?usp=sharing). ## Added - texture atlas creation functions in PyTorch based on the SoftRas cuda implementation - tests to compare SoftRas vs PyTorch3D implementation to verify it matches (using real shapenet data with meshes consisting of multiple textures) - benchmarks tests ## Remaining todo: - add more tests for obj io to test the new functions and the two texturing options - replace the shapenet data with the output from SoftRas saved as a file. # MAIN FILES TO REVIEW - `obj_io.py` - `test_obj_io.py` [still some tests to be added but have comparisons with SoftRas for now] The reference SoftRas implementations are in `softras_load_obj.py` and `load_textures.cu`. Reviewed By: gkioxari Differential Revision: D20754859 fbshipit-source-id: 42ace9dfb73f26e29d800c763f56d5b66c60c5e2
-
- 23 Apr, 2020 2 commits
-
-
Jeremy Reizenstein authored
Summary: Use aten instead of torch interface in all cuda code. This allows the cuda build to work with pytorch 1.5 with GCC 5 (e.g. the compiler of ubuntu 16.04LTS). This wasn't working. It has been failing with errors like the below, perhaps due to a bug in nvcc. ``` torch/include/torch/csrc/api/include/torch/nn/cloneable.h:68:61: error: invalid static_cast from type ‘const torch::OrderedDict<std::basic_string<char>, std::shared_ptr<torch::nn::Module> >’ to type ‘torch::OrderedDict<std::basic_string<char>, std::shared_ptr<torch::nn::Module> > ``` Reviewed By: nikhilaravi Differential Revision: D21204029 fbshipit-source-id: ca6bdbcecf42493365e1c23a33fe35e1759fe8b6
-
Roman Shapovalov authored
Summary: davnov134 found that the algorithm crashes if X is an axis-aligned plane. This is because I implemented scaling control points by `X.std()` as a poor man’s version of PCA whitening. I checked that it does not bring consistent improvements, so let’s get rid of it. The algorithm still results in slightly higher errors on the axis aligned planes but at least it does not crash. As a next step, I will experiment with detecting a planar case and using 3-point barycentric coordinates rather than 4-points. Reviewed By: davnov134 Differential Revision: D21179968 fbshipit-source-id: 1f002fce5541934486b51808be0e910324977222
-
- 22 Apr, 2020 5 commits
-
-
Justin Johnson authored
Summary: We have multiple KNN CUDA implementations. From python, users can currently request a particular implementation via the `version` flag, but they have no way of knowing which implementations can be used for a given problem. This diff exposes a function `pytorch3d._C.knn_check_version(version, D, K)` that returns whether a particular version can be used. Reviewed By: nikhilaravi Differential Revision: D21162573 fbshipit-source-id: 6061960bdcecba454fd920b00036f4e9ff3fdbc0
-
Nikhila Ravi authored
Reviewed By: gkioxari Differential Revision: D21180328 fbshipit-source-id: 218919c614c1ea54b5147871bd91960b8346524b
-
Jeremy Reizenstein authored
Summary: Modify test_chamfer for more robustness. Avoid empty pointclouds, including where point_reduction is mean, for which we currently return nan (*), and so that we aren't looking at an empty gradient. Make sure we aren't using padding as points in the homogenous cases in the tests, which will lead to a tie between closest points and therefore a potential instability in the gradient - see https://github.com/pytorch/pytorch/issues/35699. (*) This doesn't attempt to fix the nan. Reviewed By: nikhilaravi, gkioxari Differential Revision: D21157322 fbshipit-source-id: a609e84e25a24379c8928ff645d587552526e4af
-
Jeremy Reizenstein authored
Summary: cuda 10.2 location on linux. Also remove unused conda test dependencies. Reviewed By: nikhilaravi Differential Revision: D21176409 fbshipit-source-id: dd3f339a92233ff16877ba76506ddf8f4418715d
-
Nikhila Ravi authored
Summary: Added backface culling as an option to the `raster_settings`. This is needed for the full forward rendering of shapenet meshes with texture (some meshes contain multiple overlapping segments which have different textures). For a triangle (v0, v1, v2) define the vectors A = (v1 - v0) and B = (v2 − v0) and use this to calculate the area of the triangle as: ``` area = 0.5 * A x B area = 0.5 * ((x1 − x0)(y2 − y0) − (x2 − x0)(y1 − y0)) ``` The area will be positive if (v0, v1, v2) are oriented counterclockwise (a front face), and negative if (v0, v1, v2) are oriented clockwise (a back face). We can reuse the `edge_function` as it already calculates the triangle area. Reviewed By: jcjohnson Differential Revision: D20960115 fbshipit-source-id: 2d8a4b9ccfb653df18e79aed8d05c7ec0f057ab1
-
- 21 Apr, 2020 3 commits
-
-
charleschiu2012 authored
Summary: fix Args' definition at line 1016, 1018, 1020 in function pytorch3d.renderer.cameras.look_at_view_transform. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/120 Reviewed By: bottler Differential Revision: D20597565 Pulled By: nikhilaravi fbshipit-source-id: e10a221e3dccc0adf20b26808ad67328408a4388
-
Jeremy Reizenstein authored
Summary: Add conda packages for pytorch 1.5. Make wheels be only pytorch 1.5. Note that pytorch 1.4 has conda packages for cuda 9.2, 10.0 and 10.1, whilst pytorch 1.5 has packages for cuda 9.2, 10.1 and 10.2. We mirror these choices. Reviewed By: nikhilaravi Differential Revision: D21157392 fbshipit-source-id: 2f7311e6a83774a6d6c8afb8110b8bd9f37f1454
-
Georgia Gkioxari authored
Summary: Making meshrcnn compatible with new PyTorch3D features/API changes. Reviewed By: nikhilaravi Differential Revision: D21149516 fbshipit-source-id: 1c7b8c1c1f5a2abe7d379fee10ded5d2db21515a
-
- 20 Apr, 2020 2 commits
-
-
Nikhila Ravi authored
Summary: Fix a bug which resulted in a rendering artifacts if the image size was not a multiple of 16. Fix: Revert coarse rasterization to original implementation and only update fine rasterization to reverse the ordering of Y and X axis. This is much simpler than the previous approach! Additional changes: - updated mesh rendering end-end tests to check outputs from both naive and coarse to fine rasterization. - added pointcloud rendering end-end tests Reviewed By: gkioxari Differential Revision: D21102725 fbshipit-source-id: 2e7e1b013dd6dd12b3a00b79eb8167deddb2e89a
-
Jeremy Reizenstein authored
Summary: None of the current test_build tests make sense during `conda build`. Also remove the unnecessary dependency on the `six` library. Reviewed By: nikhilaravi Differential Revision: D20893852 fbshipit-source-id: 685f0446eaa0bd9151eeee89fc630a1ddc0252ff
-
- 17 Apr, 2020 7 commits
-
-
Jeremy Reizenstein authored
Summary: mostly recent lintish things Reviewed By: nikhilaravi Differential Revision: D21089003 fbshipit-source-id: 028733c1d875268f1879e4481da475b7100ba0b6
-
Jeremy Reizenstein authored
Summary: This is mostly replacing the old PackedTensorAccessor with the new PackedTensorAccessor64. Reviewed By: gkioxari Differential Revision: D21088773 fbshipit-source-id: 5973e5a29d934eafb7c70ec5ec154ca076b64d27
-
Jeremy Reizenstein authored
Reviewed By: gkioxari Differential Revision: D21088730 fbshipit-source-id: f8c125ac8c8009d45712ae63237ca64acf1faf45
-
Jeremy Reizenstein authored
Summary: A couple of files for the removed nearest_neighbor functionality are left behind. Reviewed By: nikhilaravi Differential Revision: D21088624 fbshipit-source-id: 4bb29016b4e5f63102765b384c363733b60032fa
-
Roman Shapovalov authored
Summary: Efficient PnP algorithm to fit 2D to 3D correspondences under perspective assumption. Benchmarked both variants of nullspace and pick one; SVD takes 7 times longer in the 100K points case. Reviewed By: davnov134, gkioxari Differential Revision: D20095754 fbshipit-source-id: 2b4519729630e6373820880272f674829eaed073
-
David Novotny authored
Summary: Made a CameraBase class. Added `unproject_points` method for each camera class. Reviewed By: nikhilaravi Differential Revision: D20373602 fbshipit-source-id: 7e3da5ae420091b5fcab400a9884ef29ad7a7343
-
David Novotny authored
Summary: Estimates normals of a point cloud. Reviewed By: gkioxari Differential Revision: D20860182 fbshipit-source-id: 652ec2743fa645e02c01ffa37c2971bf27b89cef
-
- 16 Apr, 2020 4 commits
-
-
David Novotny authored
Summary: The iterative closest point algorithm - point-to-point version. Output of `bm_iterative_closest_point`: Argument key: `batch_size dim n_points_X n_points_Y use_pointclouds` ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- IterativeClosestPoint_1_3_100_100_False 107569 111323 5 IterativeClosestPoint_1_3_100_1000_False 118972 122306 5 IterativeClosestPoint_1_3_1000_100_False 108576 110978 5 IterativeClosestPoint_1_3_1000_1000_False 331836 333515 2 IterativeClosestPoint_1_20_100_100_False 134387 137842 4 IterativeClosestPoint_1_20_100_1000_False 149218 153405 4 IterativeClosestPoint_1_20_1000_100_False 414248 416595 2 IterativeClosestPoint_1_20_1000_1000_False 374318 374662 2 IterativeClosestPoint_10_3_100_100_False 539852 539852 1 IterativeClosestPoint_10_3_100_1000_False 752784 752784 1 IterativeClosestPoint_10_3_1000_100_False 1070700 1070700 1 IterativeClosestPoint_10_3_1000_1000_False 1164020 1164020 1 IterativeClosestPoint_10_20_100_100_False 374548 377337 2 IterativeClosestPoint_10_20_100_1000_False 472764 476685 2 IterativeClosestPoint_10_20_1000_100_False 1457175 1457175 1 IterativeClosestPoint_10_20_1000_1000_False 2195820 2195820 1 IterativeClosestPoint_1_3_100_100_True 110084 115824 5 IterativeClosestPoint_1_3_100_1000_True 142728 147696 4 IterativeClosestPoint_1_3_1000_100_True 212966 213966 3 IterativeClosestPoint_1_3_1000_1000_True 369130 375114 2 IterativeClosestPoint_10_3_100_100_True 354615 355179 2 IterativeClosestPoint_10_3_100_1000_True 451815 452704 2 IterativeClosestPoint_10_3_1000_100_True 511833 511833 1 IterativeClosestPoint_10_3_1000_1000_True 798453 798453 1 -------------------------------------------------------------------------------- ``` Reviewed By: shapovalov, gkioxari Differential Revision: D19909952 fbshipit-source-id: f77fadc88fb7c53999909d594114b182ee2a3def
-
Nikhila Ravi authored
Summary: It seemed that even though the chamfer diff was rebased on top of the knn autograd diff, some of the final updates did not get applied. I'm really surprised that the sandcastle tests did not fail and prevent the diff from landing. Reviewed By: gkioxari Differential Revision: D21066156 fbshipit-source-id: 5216efe95180c1b6082d0bac404fa1920cfb7b02
-
Nikhila Ravi authored
Summary: Resolved trailing whitespace warnings. Reviewed By: gkioxari Differential Revision: D21023982 fbshipit-source-id: 14ea2ca372c13cfa987acc260264ca99ce44c461
-
Nikhila Ravi authored
Summary: knn is more general and faster than the nearest_neighbor code, so remove the latter. Reviewed By: gkioxari Differential Revision: D20816424 fbshipit-source-id: 75d6c44d17180752d0c9859814bbdf7892558158
-
- 15 Apr, 2020 3 commits
-
-
Nikhila Ravi authored
Summary: Allow Pointclouds objects and heterogenous data to be provided for Chamfer loss. Remove "none" as an option for point_reduction because it doesn't make sense and in the current implementation is effectively the same as "sum". Possible improvement: create specialised operations for sum and cosine_similarity of padded tensors, to avoid having to create masks. sum would be useful elsewhere. Reviewed By: gkioxari Differential Revision: D20816301 fbshipit-source-id: 0f32073210225d157c029d80de450eecdb64f4d2
-
Siddhant Ranade authored
Summary: Fixed a bug in creating the projection matrix for the SfMPerspectiveCameras class. Also fixed the corresponding test in test_cameras.py. The p0x, p0y are 2D coordinates for the principal point in the NDCS, and therefore should be added AFTER the perspective z divide. I.e. we expect <a href="https://www.codecogs.com/eqnedit.php?latex=\begin{bmatrix}&space;x\&space;y\&space;z&space;\end{bmatrix}_{\text{NDCS}}&space;=&space;\begin{bmatrix}&space;f_xX/Z&space;+&space;p_x\&space;f_yY/Z&space;+&space;p_y\&space;1&space;/&space;Z\&space;\end{bmatrix}&space;=&space;\text{normalize}\left(&space;\begin{bmatrix}&space;f_xX&space;+&space;p_xZ\&space;f_yY&space;+&space;p_yZ\&space;1\&space;Z&space;\end{bmatrix}&space;\right)" target="_blank"><img src="https://latex.codecogs.com/gif.latex?\begin{bmatrix}&space;x\&space;y\&space;z&space;\end{bmatrix}_{\text{NDCS}}&space;=&space;\begin{bmatrix}&space;f_xX/Z&space;+&space;p_x\&space;f_yY/Z&space;+&space;p_y\&space;1&space;/&space;Z\&space;\end{bmatrix}&space;=&space;\text{normalize}\left(&space;\begin{bmatrix}&space;f_xX&space;+&space;p_xZ\&space;f_yY&space;+&space;p_yZ\&space;1\&space;Z&space;\end{bmatrix}&space;\right)" title="\begin{bmatrix} x\ y\ z \end{bmatrix}_{\text{NDCS}} = \begin{bmatrix} f_xX/Z + p_x\ f_yY/Z + p_y\ 1 / Z\ \end{bmatrix} = \text{normalize}\left( \begin{bmatrix} f_xX + p_xZ\ f_yY + p_yZ\ 1\ Z \end{bmatrix} \right)" /></a> The current behavior is <a href="https://www.codecogs.com/eqnedit.php?latex=\begin{bmatrix}&space;x\&space;y\&space;z&space;\end{bmatrix}_{\text{NDCS}}&space;=&space;\begin{bmatrix}&space;f_xX/Z&space;+&space;p_x/Z\&space;f_yY/Z&space;+&space;p_y/Z\&space;1&space;/&space;Z\&space;\end{bmatrix}&space;=&space;\text{normalize}\left(&space;\begin{bmatrix}&space;f_xX&space;+&space;p_x\&space;f_yY&space;+&space;p_y\&space;1\&space;Z&space;\end{bmatrix}&space;\right)" target="_blank"><img src="https://latex.codecogs.com/gif.latex?\begin{bmatrix}&space;x\&space;y\&space;z&space;\end{bmatrix}_{\text{NDCS}}&space;=&space;\begin{bmatrix}&space;f_xX/Z&space;+&space;p_x/Z\&space;f_yY/Z&space;+&space;p_y/Z\&space;1&space;/&space;Z\&space;\end{bmatrix}&space;=&space;\text{normalize}\left(&space;\begin{bmatrix}&space;f_xX&space;+&space;p_x\&space;f_yY&space;+&space;p_y\&space;1\&space;Z&space;\end{bmatrix}&space;\right)" title="\begin{bmatrix} x\ y\ z \end{bmatrix}_{\text{NDCS}} = \begin{bmatrix} f_xX/Z + p_x/Z\ f_yY/Z + p_y/Z\ 1 / Z\ \end{bmatrix} = \text{normalize}\left( \begin{bmatrix} f_xX + p_x\ f_yY + p_y\ 1\ Z \end{bmatrix} \right)" /></a> which is incorrect. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/148 Reviewed By: gkioxari Differential Revision: D21039003 Pulled By: davnov134 fbshipit-source-id: 3e19ac22adbcc39b731ae14052a72fd4ddda2af5
-
Georgia Gkioxari authored
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
-
- 11 Apr, 2020 1 commit
-
-
Georgia Gkioxari authored
Summary: Implementation of point to mesh distances. The current diff contains two types: (a) Point to Edge (b) Point to Face ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- POINT_MESH_EDGE_4_100_300_5000_cuda:0 2745 3138 183 POINT_MESH_EDGE_4_100_300_10000_cuda:0 4408 4499 114 POINT_MESH_EDGE_4_100_3000_5000_cuda:0 4978 5070 101 POINT_MESH_EDGE_4_100_3000_10000_cuda:0 9076 9187 56 POINT_MESH_EDGE_4_1000_300_5000_cuda:0 1411 1487 355 POINT_MESH_EDGE_4_1000_300_10000_cuda:0 4829 5030 104 POINT_MESH_EDGE_4_1000_3000_5000_cuda:0 7539 7620 67 POINT_MESH_EDGE_4_1000_3000_10000_cuda:0 12088 12272 42 POINT_MESH_EDGE_8_100_300_5000_cuda:0 3106 3222 161 POINT_MESH_EDGE_8_100_300_10000_cuda:0 8561 8648 59 POINT_MESH_EDGE_8_100_3000_5000_cuda:0 6932 7021 73 POINT_MESH_EDGE_8_100_3000_10000_cuda:0 24032 24176 21 POINT_MESH_EDGE_8_1000_300_5000_cuda:0 5272 5399 95 POINT_MESH_EDGE_8_1000_300_10000_cuda:0 11348 11430 45 POINT_MESH_EDGE_8_1000_3000_5000_cuda:0 17478 17683 29 POINT_MESH_EDGE_8_1000_3000_10000_cuda:0 25961 26236 20 POINT_MESH_EDGE_16_100_300_5000_cuda:0 8244 8323 61 POINT_MESH_EDGE_16_100_300_10000_cuda:0 18018 18071 28 POINT_MESH_EDGE_16_100_3000_5000_cuda:0 19428 19544 26 POINT_MESH_EDGE_16_100_3000_10000_cuda:0 44967 45135 12 POINT_MESH_EDGE_16_1000_300_5000_cuda:0 7825 7937 64 POINT_MESH_EDGE_16_1000_300_10000_cuda:0 18504 18571 28 POINT_MESH_EDGE_16_1000_3000_5000_cuda:0 65805 66132 8 POINT_MESH_EDGE_16_1000_3000_10000_cuda:0 90885 91089 6 -------------------------------------------------------------------------------- Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- POINT_MESH_FACE_4_100_300_5000_cuda:0 1561 1685 321 POINT_MESH_FACE_4_100_300_10000_cuda:0 2818 2954 178 POINT_MESH_FACE_4_100_3000_5000_cuda:0 15893 16018 32 POINT_MESH_FACE_4_100_3000_10000_cuda:0 16350 16439 31 POINT_MESH_FACE_4_1000_300_5000_cuda:0 3179 3278 158 POINT_MESH_FACE_4_1000_300_10000_cuda:0 2353 2436 213 POINT_MESH_FACE_4_1000_3000_5000_cuda:0 16262 16336 31 POINT_MESH_FACE_4_1000_3000_10000_cuda:0 9334 9448 54 POINT_MESH_FACE_8_100_300_5000_cuda:0 4377 4493 115 POINT_MESH_FACE_8_100_300_10000_cuda:0 9728 9822 52 POINT_MESH_FACE_8_100_3000_5000_cuda:0 26428 26544 19 POINT_MESH_FACE_8_100_3000_10000_cuda:0 42238 43031 12 POINT_MESH_FACE_8_1000_300_5000_cuda:0 3891 3982 129 POINT_MESH_FACE_8_1000_300_10000_cuda:0 5363 5429 94 POINT_MESH_FACE_8_1000_3000_5000_cuda:0 20998 21084 24 POINT_MESH_FACE_8_1000_3000_10000_cuda:0 39711 39897 13 POINT_MESH_FACE_16_100_300_5000_cuda:0 5955 6001 84 POINT_MESH_FACE_16_100_300_10000_cuda:0 12082 12144 42 POINT_MESH_FACE_16_100_3000_5000_cuda:0 44996 45176 12 POINT_MESH_FACE_16_100_3000_10000_cuda:0 73042 73197 7 POINT_MESH_FACE_16_1000_300_5000_cuda:0 8292 8374 61 POINT_MESH_FACE_16_1000_300_10000_cuda:0 19442 19506 26 POINT_MESH_FACE_16_1000_3000_5000_cuda:0 36059 36194 14 POINT_MESH_FACE_16_1000_3000_10000_cuda:0 64644 64822 8 -------------------------------------------------------------------------------- ``` Reviewed By: jcjohnson Differential Revision: D20590462 fbshipit-source-id: 42a39837b514a546ac9471bfaff60eefe7fae829
-
- 08 Apr, 2020 1 commit
-
-
Nikhila Ravi authored
Summary: Remove `bin_size` and `max_faces_per_pixel` from being specified. This means the coarse-to-fine rasterization will be used by default and will help avoid confusion with the naive version. Reviewed By: jcjohnson Differential Revision: D20908905 fbshipit-source-id: c181c88e844d888aa81a36870918307961dc1175
-
- 07 Apr, 2020 2 commits
-
-
Jeremy Reizenstein authored
Summary: Pytorch 1.5 is coming soon. I imagine we will want the ability to upload conda packages for pytorch3d to anaconda cloud for each of pytorch 1.4 and pytorch 1.5. This change adds the dependent pytorch version to the name of the conda package to make that feasible. As an example, a built package after this change will have a name like `linux-64/pytorch3d-0.1.1-py38_cu100_pyt14.tar.bz2`, instead of simply `linux-64/pytorch3d-0.1.1-py38_cu100.tar.bz2`. Also some tiny cleanup of circleci config. Other alternatives: (1) forcing users to update pytorch and pytorch3d together, (2) trying to get away with one build for multiple pytorch versions. Reviewed By: nikhilaravi Differential Revision: D20599039 fbshipit-source-id: 20164eda4a5141afed47b3596e559950d796ffc9
-
Jeremy Reizenstein authored
Summary: Interface and working implementation of ragged KNN. Benchmarks (which aren't ragged) haven't slowed. New benchmark shows that ragged is faster than non-ragged of the same shape. Reviewed By: jcjohnson Differential Revision: D20696507 fbshipit-source-id: 21b80f71343a3475c8d3ee0ce2680f92f0fae4de
-
- 06 Apr, 2020 2 commits
-
-
Jeremy Reizenstein authored
Summary: The conda build process generates some files of its own, which we don't want to catch in our test for copyright notices. Reviewed By: nikhilaravi, patricklabatut Differential Revision: D20868566 fbshipit-source-id: 76a786a3eb9a674d59e630cc06f346e8b82258a4
-
Jeremy Reizenstein authored
Summary: lint clean again Reviewed By: patricklabatut Differential Revision: D20868775 fbshipit-source-id: ade4301c1012c5c6943186432465215701d635a9
-
- 05 Apr, 2020 1 commit
-
-
David Novotny authored
Summary: Allows to initialize a Transform3D object with a batch of user-defined transformation matrices: ``` t = Transform3D(matrix=torch.randn(2, 4, 4)) ``` Reviewed By: nikhilaravi Differential Revision: D20693475 fbshipit-source-id: dccc49b2ca4c19a034844c63463953ba8f52c1bc
-
- 03 Apr, 2020 1 commit
-
-
Roman Shapovalov authored
Summary: 1. Introduced weights to Umeyama implementation. This will be needed for weighted ePnP but is useful on its own. 2. Refactored to use the same code for the Pointclouds mask and passed weights. 3. Added test cases with random weights. 4. Fixed a bug in tests that calls the function with 0 points (fails randomly in Pytorch 1.3, will be fixed in the next release: https://github.com/pytorch/pytorch/issues/31421 ). Reviewed By: gkioxari Differential Revision: D20070293 fbshipit-source-id: e9f549507ef6dcaa0688a0f17342e6d7a9a4336c
-
- 02 Apr, 2020 1 commit
-
-
David Novotny authored
Summary: Umeyama estimates a rigid motion between two sets of corresponding points. Benchmark output for `bm_points_alignment` ``` Arguments key: [<allow_reflection>_<batch_size>_<dim>_<estimate_scale>_<n_points>_<use_pointclouds>] Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- CorrespodingPointsAlignment_True_1_3_True_100_False 7382 9833 68 CorrespodingPointsAlignment_True_1_3_True_10000_False 8183 10500 62 CorrespodingPointsAlignment_True_1_3_False_100_False 7301 9263 69 CorrespodingPointsAlignment_True_1_3_False_10000_False 7945 9746 64 CorrespodingPointsAlignment_True_1_20_True_100_False 13706 41623 37 CorrespodingPointsAlignment_True_1_20_True_10000_False 11044 33766 46 CorrespodingPointsAlignment_True_1_20_False_100_False 9908 28791 51 CorrespodingPointsAlignment_True_1_20_False_10000_False 9523 18680 53 CorrespodingPointsAlignment_True_10_3_True_100_False 29585 32026 17 CorrespodingPointsAlignment_True_10_3_True_10000_False 29626 36324 18 CorrespodingPointsAlignment_True_10_3_False_100_False 26013 29253 20 CorrespodingPointsAlignment_True_10_3_False_10000_False 25000 33820 20 CorrespodingPointsAlignment_True_10_20_True_100_False 40955 41592 13 CorrespodingPointsAlignment_True_10_20_True_10000_False 42087 42393 12 CorrespodingPointsAlignment_True_10_20_False_100_False 39863 40381 13 CorrespodingPointsAlignment_True_10_20_False_10000_False 40813 41699 13 CorrespodingPointsAlignment_True_100_3_True_100_False 183146 194745 3 CorrespodingPointsAlignment_True_100_3_True_10000_False 213789 231466 3 CorrespodingPointsAlignment_True_100_3_False_100_False 177805 180796 3 CorrespodingPointsAlignment_True_100_3_False_10000_False 184963 185695 3 CorrespodingPointsAlignment_True_100_20_True_100_False 347181 347325 2 CorrespodingPointsAlignment_True_100_20_True_10000_False 363259 363613 2 CorrespodingPointsAlignment_True_100_20_False_100_False 351769 352496 2 CorrespodingPointsAlignment_True_100_20_False_10000_False 375629 379818 2 CorrespodingPointsAlignment_False_1_3_True_100_False 11155 13770 45 CorrespodingPointsAlignment_False_1_3_True_10000_False 10743 13938 47 CorrespodingPointsAlignment_False_1_3_False_100_False 9578 11511 53 CorrespodingPointsAlignment_False_1_3_False_10000_False 9549 11984 53 CorrespodingPointsAlignment_False_1_20_True_100_False 13809 14183 37 CorrespodingPointsAlignment_False_1_20_True_10000_False 14084 15082 36 CorrespodingPointsAlignment_False_1_20_False_100_False 12765 14177 40 CorrespodingPointsAlignment_False_1_20_False_10000_False 12811 13096 40 CorrespodingPointsAlignment_False_10_3_True_100_False 28823 39384 18 CorrespodingPointsAlignment_False_10_3_True_10000_False 27135 27525 19 CorrespodingPointsAlignment_False_10_3_False_100_False 26236 28980 20 CorrespodingPointsAlignment_False_10_3_False_10000_False 42324 45123 12 CorrespodingPointsAlignment_False_10_20_True_100_False 723902 723902 1 CorrespodingPointsAlignment_False_10_20_True_10000_False 220007 252886 3 CorrespodingPointsAlignment_False_10_20_False_100_False 55593 71636 9 CorrespodingPointsAlignment_False_10_20_False_10000_False 44419 71861 12 CorrespodingPointsAlignment_False_100_3_True_100_False 184768 185199 3 CorrespodingPointsAlignment_False_100_3_True_10000_False 198657 213868 3 CorrespodingPointsAlignment_False_100_3_False_100_False 224598 309645 3 CorrespodingPointsAlignment_False_100_3_False_10000_False 197863 202002 3 CorrespodingPointsAlignment_False_100_20_True_100_False 293484 309459 2 CorrespodingPointsAlignment_False_100_20_True_10000_False 327253 366644 2 CorrespodingPointsAlignment_False_100_20_False_100_False 420793 422194 2 CorrespodingPointsAlignment_False_100_20_False_10000_False 462634 485542 2 CorrespodingPointsAlignment_True_1_3_True_100_True 7664 9909 66 CorrespodingPointsAlignment_True_1_3_True_10000_True 7190 8366 70 CorrespodingPointsAlignment_True_1_3_False_100_True 6549 8316 77 CorrespodingPointsAlignment_True_1_3_False_10000_True 6534 7710 77 CorrespodingPointsAlignment_True_10_3_True_100_True 29052 32940 18 CorrespodingPointsAlignment_True_10_3_True_10000_True 30526 33453 17 CorrespodingPointsAlignment_True_10_3_False_100_True 28708 32993 18 CorrespodingPointsAlignment_True_10_3_False_10000_True 30630 35973 17 CorrespodingPointsAlignment_True_100_3_True_100_True 264909 320820 3 CorrespodingPointsAlignment_True_100_3_True_10000_True 310902 322604 2 CorrespodingPointsAlignment_True_100_3_False_100_True 246832 250634 3 CorrespodingPointsAlignment_True_100_3_False_10000_True 276006 289061 2 CorrespodingPointsAlignment_False_1_3_True_100_True 11421 13757 44 CorrespodingPointsAlignment_False_1_3_True_10000_True 11199 12532 45 CorrespodingPointsAlignment_False_1_3_False_100_True 11474 15841 44 CorrespodingPointsAlignment_False_1_3_False_10000_True 10384 13188 49 CorrespodingPointsAlignment_False_10_3_True_100_True 36599 47340 14 CorrespodingPointsAlignment_False_10_3_True_10000_True 40702 50754 13 CorrespodingPointsAlignment_False_10_3_False_100_True 41277 52149 13 CorrespodingPointsAlignment_False_10_3_False_10000_True 34286 37091 15 CorrespodingPointsAlignment_False_100_3_True_100_True 254991 258578 2 CorrespodingPointsAlignment_False_100_3_True_10000_True 257999 261285 2 CorrespodingPointsAlignment_False_100_3_False_100_True 247511 248693 3 CorrespodingPointsAlignment_False_100_3_False_10000_True 251807 263865 3 ``` Reviewed By: gkioxari Differential Revision: D19808389 fbshipit-source-id: 83305a58627d2fc5dcaf3c3015132d8148f28c29
-
- 01 Apr, 2020 2 commits
-
-
Patrick Labatut authored
Summary: Do not create output files with invalid inputs to `save_{obj,ply}()`. Reviewed By: bottler Differential Revision: D20720282 fbshipit-source-id: 3b611a10da6f6eecacab2a1900bf16f89e2000aa -
Patrick Labatut authored
Summary: Similar to D20392526, PLY files without vertices or faces should be allowed: - a PLY with only vertices can represent a point cloud - a PLY without any vertex or face is just empty - a PLY with faces referencing inexistent vertices has invalid data Reviewed By: gkioxari Differential Revision: D20400330 fbshipit-source-id: 35a5f072603fd221f382c7faad5f37c3e0b49bb1
-
