GitLab

Summary: Flowing of compositing comments

Reviewed By: nikhilaravi

Differential Revision: D20556707

fbshipit-source-id: 4abdc85e4f65abd41c4a890b6895bc5e95b4576b

Summary: Address black + isort fbsource linter warnings from D20558374 (previous diff)

Reviewed By: nikhilaravi

Differential Revision: D20558373

fbshipit-source-id: d3607de4a01fb24c0d5269634563a7914bddf1c8

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: Small website fix.

Reviewed By: bottler

Differential Revision: D20672621

fbshipit-source-id: b787e626f732a8abdd92c29e5e4e8bbe27bc7e2f

Summary:
Replace `tensor.type().is_cuda()` with the preferred `tensor.is_cuda()`.
Replace `AT_DISPATCH_FLOATING_TYPES(tensor.type(), ...` with `AT_DISPATCH_FLOATING_TYPES(tensor.scalar_type(), ...`.
These avoid deprecation warnings in future pytorch.

Reviewed By: nikhilaravi

Differential Revision: D20646565

fbshipit-source-id: 1a0c15978c871af816b1dd7d4a7ea78242abd95e

Summary: replace `data()` with preferred `data_ptr()`, avoiding some deprecation warnings in future pytorch.

Reviewed By: nikhilaravi

Differential Revision: D20645738

fbshipit-source-id: 8f6e02d292729b804fa2a66f94dd0517bbaf7887

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: Run `/dev/linter.sh` to fix linting

Reviewed By: nikhilaravi

Differential Revision: D20584037

fbshipit-source-id: 69e45b33d22e3d54b6d37c3c35580bb3e9dc50a5

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: Replace view with reshape, add check for nans before mesh sampling

Reviewed By: nikhilaravi

Differential Revision: D20548456

fbshipit-source-id: c4e1b88e033ecb8f0f3a8f3a33a04ce13a5b5043

Summary:
Code for accumulating points in the z-buffer in three ways:
1. weighted sum
2. normalised weighted sum
3. alpha compositing

Pull Request resolved: https://github.com/fairinternal/pytorch3d/pull/4

Reviewed By: nikhilaravi

Differential Revision: D20522422

Pulled By: gkioxari

fbshipit-source-id: 5023baa05f15e338f3821ef08f5552c2dcbfc06c

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

Re-sync with internal repository

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: Enable spelling linter for Markdown, reStructuredText and IPython notebooks under `fbcode/vision/fair`. Apply suggested fixes.

Reviewed By: ppwwyyxx

Differential Revision: D20495298

fbshipit-source-id: 95310c7b51f9fa68ba2aa34ecc39a874da36a75c

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:
Fix errors raised by issue on GitHub - extending mesh textures + rendering with Gourad and Phong shaders.

https://github.com/facebookresearch/pytorch3d/issues/97

Reviewed By: gkioxari

Differential Revision: D20319610

fbshipit-source-id: d1c692ff0b9397a77a9b829c5c731790de70c09f

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: Ensure copyright header consistency and translation unit name uniqueness.

Reviewed By: nikhilaravi

Differential Revision: D20438802

fbshipit-source-id: 9820cfe4c6efab016a0a8589dfa24bb526692f83

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 more complex mesh I/O benchmarks: simple yet non-trivial procedural donut mesh

Reviewed By: nikhilaravi

Differential Revision: D20390726

fbshipit-source-id: b28b7e3a7f1720823c6bd24faabf688bb0127b7d

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 benchmarking methods: always (re-)create file-like object and directly return a lambda

Reviewed By: nikhilaravi

Differential Revision: D20390723

fbshipit-source-id: b45236360869cccdf3d5458a0aafb3ebe269babe

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

Reviewed By: nikhilaravi

Differential Revision: D20218481

fbshipit-source-id: b153282cc30ad75de970c89ae64526b6be62ee95