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
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
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
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
Summary: Do not create output files with invalid inputs to `save_{obj,ply}()`.
Reviewed By: bottler
Differential Revision: D20720282
fbshipit-source-id: 3b611a10da6f6eecacab2a1900bf16f89e2000aa
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
Summary:
Enable `black` + `isort` (via `pyfmt`) i.e. `BLACK` fbsource linter.
NOTE: the `BLACK` fbsource linter (and `black` itself) is (by design) ***not*** configurable. This forces aligning the existing options used by the tools invoked in `dev/linter.sh` (for 3rd party developers) with `BLACK` fbsource linting. Without this reconciliation, the different linters (used internally or by 3rd party developers) would simply conflict with each other resulting in artificial back-and-forth changes (for instance line width which `BLACK` forces to 88 characters).
Reviewed By: nikhilaravi
Differential Revision: D20558374
fbshipit-source-id: 614fa00664f8eb9d2de7438c29b807dfbf36ad20
Summary: Run linter after recent changes. Fix long comment in knn.h which clang-format has reflowed badly. Add crude test that code doesn't call deprecated `.type()` or `.data()`.
Reviewed By: nikhilaravi
Differential Revision: D20692935
fbshipit-source-id: 28ce0308adae79a870cb41a810b7cf8744f41ab8
Summary:
OBJ files without vertices or faces should be allowed:
- an OBJ with only vertices can represent a point cloud
- an OBJ without any vertex or face is just empty
- an OBJ with faces referencing inexistent vertices has invalid data
Reviewed By: gkioxari
Differential Revision: D20392526
fbshipit-source-id: e72c846ff1e5787fb11d527af3fefa261f9eb0ee
Summary:
Implements K-Nearest Neighbors with C++ and CUDA versions.
KNN in CUDA is highly nontrivial. I've implemented a few different versions of the kernel, and we heuristically dispatch to different kernels based on the problem size. Some of the kernels rely on template specialization on either D or K, so we use template metaprogramming to compile specialized versions for ranges of D and K.
These kernels are up to 3x faster than our existing 1-nearest-neighbor kernels, so we should also consider swapping out `nn_points_idx` to use these kernels in the backend.
I've been working mostly on the CUDA kernels, and haven't converged on the correct Python API.
I still want to benchmark against FAISS to see how far away we are from their performance.
Reviewed By: bottler
Differential Revision: D19729286
fbshipit-source-id: 608ffbb7030c21fe4008f330522f4890f0c3c21a
Summary: CPU-only builds should be fixed by this change
Reviewed By: nikhilaravi
Differential Revision: D20598014
fbshipit-source-id: df098ec4c6c93d38515172805fe57cac7463c506
Summary: use assertClose in some tests, which enforces shape equality. Fixes some small problems, including graph_conv on an empty graph.
Reviewed By: nikhilaravi
Differential Revision: D20556912
fbshipit-source-id: 60a61eafe3c03ce0f6c9c1a842685708fb10ac5b
Summary: By accident I think, we have been nudging people to install python 3.6. Using 3.8 is fine.
Reviewed By: nikhilaravi
Differential Revision: D20597240
fbshipit-source-id: 7fb778f1b84746db28b6eef763564af5c5fffcd7
Summary:
Add a note about the difference between naive and coarse-to-fine rasterization to all the rendering tutorials.
Update the render pointclouds tutorial to wget the data file.
Reviewed By: gkioxari
Differential Revision: D20575257
fbshipit-source-id: a2806b9452438f97cb754f87e011c6e32e2545e4
Summary: Add pattern linter for PyTorch3D and SlowFast, this will suggest typo fixes whenever the wrong case is accidentally used.
Reviewed By: wanyenlo
Differential Revision: D20498696
fbshipit-source-id: 1a3f4702bd0dbe06e81d0f301b3ea38ea62e7885
Summary:
Create extrinsic parameters from eye point.
Create the rotation and translation from an eye point, look-at point and up vector.
see:
https://www.khronos.org/registry/OpenGL-Refpages/gl2.1/xhtml/gluLookAt.xml
It is arguably easier to initialise a camera position as a point in the world rather than an angle.
Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/65
Reviewed By: bottler
Differential Revision: D20419652
Pulled By: nikhilaravi
fbshipit-source-id: 9caa1330860bb8bde1fb5c3864ed4cde836a5d19
Summary:
A few small website updates:
- changed the tutorials to point to the `stable` tag on github so we don't have to update the website each time we want to run them!
- changed the colab button
- re ran notebook cells to update the images for textured meshes
Once these fixes are landed I can build and publish the website.
Reviewed By: bottler
Differential Revision: D20484836
fbshipit-source-id: 603a05e752f631c60d1a3abb9adeb1b9b451ab98
Summary: Use a consistent case for PyTorch3D (matching the logo...): replace all occurrences of PyTorch3d with PyTorch3D across the codebase (including documentation and notebooks)
Reviewed By: wanyenlo, gkioxari
Differential Revision: D20427546
fbshipit-source-id: 8c7697f51434c51e99b7fe271935932c72a1d9b9
Summary: D20426113 made a mistake, in that it added a dev tag to all conda builds. This makes the simplest fix, which is to never have the dev tag.
Reviewed By: nikhilaravi
Differential Revision: D20468541
fbshipit-source-id: adc71b58d59356834d33f65a75cf8ba84359bc74
Summary: Added a padded to packed utils function which takes either split sizes or a padding value to remove padded elements from a tensor.
Reviewed By: gkioxari
Differential Revision: D20454238
fbshipit-source-id: 180b807ff44c74c4ee9d5c1ac3b5c4a9b4be57c7
Summary:
This isn't the whole task, but it gets the version number into far fewer places.
The doc / website are separate.
Reviewed By: nikhilaravi
Differential Revision: D20426113
fbshipit-source-id: 5810d1eca58b443fcd5f46991dc2f0f26adedbd8
Summary: Comments were describing squared distance as absolute distance in a few places.
Reviewed By: nikhilaravi
Differential Revision: D20426020
fbshipit-source-id: 009946867c4a98f61f5ce7158542d41e22bf8346
Summary: Add utility function to tesselate a torus, to be used in more complex mesh I/O benchmarks
Reviewed By: bottler
Differential Revision: D20390724
fbshipit-source-id: 882bbbe9cac81cf340a34495b9aa66e3c1ddeebc
Summary: Use more realistic number of vertices / faces in benchmarks: in typical meshes, |F| ~ 2 |V| (follows from Euler formula + triangles as faces)
Reviewed By: nikhilaravi
Differential Revision: D20390722
fbshipit-source-id: d615e5810d6f4521391963b2573497c08a58db80
Summary:
Rename mesh I/O benchmarks and associated methods:
- add `simple` qualifier (benchmark on more realistic mesh data to be added later)
- align naming between OBJ and PLY
- prefix with `bm_` to make the benchmarking purpose clear(er)
Reviewed By: nikhilaravi
Differential Revision: D20390764
fbshipit-source-id: 7714520abfcfe1125067f3c52f7ce19bca359574
Summary: The shebang line `#!<path to interpreter>` is only required for Python scripts, so remove it on source files for class or function definitions. Additionally explicitly mark as executable the actual Python scripts in the codebase.
Reviewed By: nikhilaravi
Differential Revision: D20095778
fbshipit-source-id: d312599fba485e978a243292f88a180d71e1b55a
Summary:
Applying the changes added for mesh rasterization to ensure that +Y is up and +X is left so that the coordinate system is right handed.
Also updated the diagram in the docs to indicate that (0,0) is in the top left hand corner.
Reviewed By: gkioxari
Differential Revision: D20394849
fbshipit-source-id: cfb7c79090eb1f55ad38b92327a74a70a8dc541e
Summary:
Update the point cloud rasterizer to:
- use the pointcloud datastructure (rebased on top of D19791851.)
- support rasterization of heterogeneous point clouds in the same way as with Meshes.
The main changes to the API will be as follows:
- The input to `rasterize_points` will be a `Pointclouds` object instead of a tensor. This will be easy to update e.g.
```
points = torch.randn(N, P, 3)
idx2, zbuf2, dists2 = rasterize_points(points, image_size, radius, points_per_pixel)
points = torch.randn(N, P, 3)
pointclouds = Pointclouds(points=points)
idx2, zbuf2, dists2 = rasterize_points(pointclouds, image_size, radius, points_per_pixel)
```
- The indices output from rasterization will now refer to points in `poinclouds.points_packed()`.
This may require some changes to the functions which consume the outputs of rasterization if they were previously
assuming that the indices ranged from 0 to P where P is the number of points in each pointcloud.
Making this change now so that Olivia can update her PR accordingly.
Reviewed By: gkioxari
Differential Revision: D20088651
fbshipit-source-id: 833ed659909712bcbbb6a50e2ec0189839f0413a
Summary: When the error occurs, another exception is thrown when tensor shape is passed to the % formatting. I have found all entries for `msg %` and fixed potential failures
Reviewed By: nikhilaravi
Differential Revision: D20386511
fbshipit-source-id: c05413eb4867cab1ddc9615dffbd0ebd3adfcaf9
Summary: Make Meshes.__getitem__ carry texture information to the new mesh.
Reviewed By: gkioxari
Differential Revision: D20283976
fbshipit-source-id: d9ee0580c11ac5b4384df9d8158a07e6eb8d00fe
