GitLab

Summary:
Error Reproduction:

python=3.8.12
pytorch=1.9.1
pytorch3d=0.6.1
cudatoolkit=11.1.74

test.py:
```python
import torch
from pytorch3d.ops import cubify
voxels = torch.Tensor([[[[0,1], [0,0]], [[0,1], [0,0]]]]).float()
meshes = cubify(voxels, 0.5, device="cpu")
```

The error appears when `device="cpu"` and `pytorch=1.9.1` (works fine with pytorch=1.10.2)

Error message:
```console
/home/kyle/anaconda3/envs/adapt-net/lib/python3.8/site-packages/torch/_tensor.py:575: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at  /opt/conda/conda-bld/pytorch_1631630839582/work/aten/src/ATen/native/BinaryOps.cpp:467.)
  return torch.floor_divide(self, other)
Traceback (most recent call last):
  File "test.py", line 5, in <module>
    meshes = cubify(voxels, 0.5, device="cpu")
  File "/home/kyle/anaconda3/envs/adapt-net/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
    return func(*args, **kwargs)
  File "/home/kyle/Desktop/pytorch3d/pytorch3d/ops/cubify.py", line 227, in cubify
    idleverts.scatter_(0, grid_faces.flatten(), 0)
RuntimeError: Expected index [60] to be smaller than self [27] apart from dimension 0 and to be smaller size than src [27]
```

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1067

Reviewed By: nikhilaravi

Differential Revision: D34893567

Pulled By: bottler

fbshipit-source-id: aa95980f7319302044141f7821ef48129cfa37a6

Summary: This is required to suppress a huge stdout full of warnings about overflown bins.

Reviewed By: bottler

Differential Revision: D35359824

fbshipit-source-id: 39214b1bdcb4a5d5debf8ed498b2ca81fa43d210

Summary: Aid reflection by adding the original declared types of replaced members of a configurable as values in _processed_members.

Reviewed By: davnov134

Differential Revision: D35358422

fbshipit-source-id: 80ef3266144c51c1c2105f349e0dd3464e230429

Summary: Use logging instead of printing in the internals of implicitron.

Reviewed By: davnov134

Differential Revision: D35247581

fbshipit-source-id: be5ddad5efe1409adbae0575d35ade6112b3be63

Summary: This might make the implicitron tests work better on RE.

Reviewed By: davnov134

Differential Revision: D35283131

fbshipit-source-id: 4dda9684f632ab6e9cebcbf1e6e4a8243ec00c85

Summary: Optional[not_a_type] was causing errors.

Reviewed By: davnov134

Differential Revision: D35355530

fbshipit-source-id: e9b52cfd6347ffae0fe688ef30523a4092ccf9fd

Summary: Pyre expects Mapping for ** operator.

Reviewed By: bottler

Differential Revision: D35288632

fbshipit-source-id: 34d6f26ad912b3a5046f440922bb6ed2fd86f533

Summary:
ListConfig and DictConfig members of get_default_args(X) when X is a callable will contain references to a temporary dataclass and therefore be unpicklable. Avoid this in a few cases.

Fixes https://github.com/facebookresearch/pytorch3d/issues/1144

Reviewed By: shapovalov

Differential Revision: D35258561

fbshipit-source-id: e52186825f52accee9a899e466967a4ff71b3d25

Summary: as subj

Reviewed By: davnov134

Differential Revision: D35194863

fbshipit-source-id: c8e8f234083d4f0f93dca8d93e090ca0e1e1972d

Summary:
Previously, dtypes were not propagated correctly in composed transforms, resulting in errors when different dtypes were mixed. Even specifying a dtype in the constructor does not fix this. Neither does specifying the dtype for each composition function invocation (e.g. as a `kwarg` in `rotate_axis_angle`).

With the change, I also had to modify the default dtype of `RotateAxisAngle`, which was `torch.float64`; it is now `torch.float32` like for all other transforms. This was required because the fix in propagation broke some tests due to dtype mismatches.

This change in default dtype in turn broke two tests due to precision changes (calculations that were previously done in `torch.float64` were now done in `torch.float32`), so I changed the precision tolerances to be less strict. I chose the lowest power of ten that passed the tests here.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1141

Reviewed By: patricklabatut

Differential Revision: D35192970

Pulled By: bottler

fbshipit-source-id: ba0293e8b3595dfc94b3cf8048e50b7a5e5ed7cf

Summary: Allow things like `renderer:Optional[BaseRenderer]` in configurables.

Reviewed By: davnov134

Differential Revision: D35118339

fbshipit-source-id: 1219321b2817ed4b26fe924c6d6f73887095c985

Summary: To ensure that tests outside implicitron/ don't use implicitron, split the test for recursive includes in to two. License header checking is not needed here any more.

Reviewed By: shapovalov

Differential Revision: D35077830

fbshipit-source-id: 2ebe7436a6dcc5d21a116434f6ddd08705dfab34

Summary: Enable `pytorch3d_implicitron_runner` executable

Reviewed By: shapovalov

Differential Revision: D34754902

fbshipit-source-id: 213f3e9183e3f7dd7b4df16ad77d95fbc971d625

Summary: Attempt to solve an internal issue

Reviewed By: shapovalov

Differential Revision: D35143263

fbshipit-source-id: b4fd9ee441d85f0a3ee08f2f1e7febd1c1ccbe86

Summary:
Before the fix, running get_default_args(C: Callable) returns an unstructured DictConfig which causes Enums to be handled incorrectly. This is a fix.

WIP update: Currently tests still fail whenever a function signature contains an untyped argument: This needs to be somehow fixed.

Reviewed By: bottler

Differential Revision: D34932124

fbshipit-source-id: ecdc45c738633cfea5caa7480ba4f790ece931e8

Summary: Some directories in implicitron were missing __init__.py files.

Reviewed By: patricklabatut

Differential Revision: D35076364

fbshipit-source-id: f74442766efe8694fdd47954ac4882e7c4daac60

Summary: bin_size should be 0 not -1 for naive rasterization. See https://github.com/facebookresearch/pytorch3d/issues/1129

Reviewed By: patricklabatut

Differential Revision: D35077115

fbshipit-source-id: b81ff74f47c78429977802f7dcadfd1b96676f8c

Summary: Attempt to reduce nvcc trouble on windows by (1) avoiding flag for c++14 and (2) avoiding `torch/extension.h`, which introduces pybind11, in `.cu` files.

Reviewed By: patricklabatut

Differential Revision: D34969868

fbshipit-source-id: f3878d6a2ba9d644e87ae7b6377cb5008b4b6ce3

Summary: Using the API from D35012121 everywhere.

Reviewed By: bottler

Differential Revision: D35045870

fbshipit-source-id: dab112b5e04160334859bbe8fa2366344b6e0f70

Summary: We often want to iterate over frames in the sequence in temporal order. This diff provides the API to do that. `seq_to_idx` should probably be considered to have `protected` visibility.

Reviewed By: davnov134

Differential Revision: D35012121

fbshipit-source-id: 41896672ec35cd62f3ed4be3aa119efd33adada1

fbshipit-source-id: d20e2f3d7ae6ca8c4a1e72002c1be8d75217939d

fbshipit-source-id: 29b8a643c0218375bf90b9c1fb8853dedd0906fe

Co-authored-by: Jeremy Francis Reizenstein <bottler@users.noreply.github.com>

Summary:
Fixes required for MC rasterisation to work.
1) Wrong number of channels for background was used (derived from points dimensions, not features dimensions;
2) split of the results on the wrong dimension was done;
3) CORE CHANGE: blending in alpha compositor was assuming RGBA input.

Reviewed By: davnov134

Differential Revision: D34933673

fbshipit-source-id: a5cc9f201ea21e114639ab9e291a10888d495206

Summary: as subj

Reviewed By: davnov134

Differential Revision: D34758227

fbshipit-source-id: c22e7c4c6e69e9ef872b46c99ece901c58c23d71

Summary: Add builds for PyTorch 1.11.0.

Reviewed By: nikhilaravi

Differential Revision: D34861021

fbshipit-source-id: 1a1c46fac48719bc66c81872e65531a48ff538ed

Summary:
1. Fix https://github.com/facebookresearch/pytorch3d/issues/1115 Change the type annatations of three arguments in the initializer of `R2N2` class.
2. Fix https://github.com/facebookresearch/pytorch3d/issues/1118 Override two functions in `BlenderCamera` class reruired by subclassing `CamerasBase` class.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1124

Reviewed By: nikhilaravi

Differential Revision: D34890900

Pulled By: bottler

fbshipit-source-id: 65c385369a5964ecbb17ab28f279d5284614b487

Summary: Fix assumption that face indices are signed in the PLY file, as reported in #1104.

Reviewed By: nikhilaravi

Differential Revision: D34892598

fbshipit-source-id: a8b23bfac1357bdc11bbbf752098319142239804

Summary: Try to fix circleci again.

Reviewed By: nikhilaravi

Differential Revision: D34752188

fbshipit-source-id: 5966c585b61d77df1d8dd97c24383cf74dfb1fae

Summary: As noticed in https://github.com/facebookresearch/pytorch3d/issues/1098 , it would be useful to make this more available.

Reviewed By: nikhilaravi

Differential Revision: D34752526

fbshipit-source-id: 5a127bd557a0cd626f36bf194f22bc0a0a6a2436

Summary: As reported in https://github.com/facebookresearch/pytorch3d/pull/1100, a rasterizer couldn't be moved if it was missing the optional cameras member. Fix that. This matters because the renderer.to calls rasterizer.to, so this to() could be called even by a user who never sets a cameras member.

Reviewed By: nikhilaravi

Differential Revision: D34643841

fbshipit-source-id: 7e26e32e8bc585eb1ee533052754a7b59bc7467a

Summary: As reported in https://github.com/facebookresearch/pytorch3d/pull/1100, _num_faces_per_mesh was changing in the source mesh in join_batch. This affects both TexturesUV and TexturesAtlas

Reviewed By: nikhilaravi

Differential Revision: D34643675

fbshipit-source-id: d67bdaca7278f18a76cfb15ba59d0ea85575bd36

Summary:
Our mission at [Meta Open Source](https://opensource.facebook.com/) is to empower communities through open source, and we believe that it means building a welcoming and safe environment for all. As a part of this work, we are adding this banner in support for Ukraine during this crisis.

![image](https://user-images.githubusercontent.com/12485205/156670302-756fac7c-51ba-4e24-b463-f79730dbaba6.png)

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1101

Reviewed By: bottler

Differential Revision: D34628257

Pulled By: dmitryvinn-fb

fbshipit-source-id: 5863afb59a2b9431e8e2ebc5856254ab0cdfcfe8

Summary: A scalar background color is not meant to be allowed for the point renderer. It used to be ignored with a warning, but a recent code change made it an error. It was being used, at least in the black (value=0.0) case. Re-enable it.

Reviewed By: nikhilaravi

Differential Revision: D34519651

fbshipit-source-id: d37dcf145bb7b8999c9265cf8fc39b084059dd18

Reviewed By: zsol

Differential Revision: D34526295

fbshipit-source-id: f511370dc3186bc396d68a2e6d5e0931facbeb42

Summary:
1. changed IsInsideTriangle in geometry_utils to take in min_triangle_area parameter instead of hardcoded value
2. updated point_mesh_cpu.cpp and point_mesh_cuda.[h/cu] to adapt to changes in geometry_utils function signatures
3. updated point_mesh_distance.py and test_point_mesh_distance.py to modify _C. calls

Reviewed By: bottler

Differential Revision: D34459764

fbshipit-source-id: 0549e78713c6d68f03d85fb597a13dd88e09b686

Summary: Small changes discovered based on circleCI failures.

Reviewed By: patricklabatut

Differential Revision: D34426807

fbshipit-source-id: 819860f34b2f367dd24057ca7490284204180a13

Summary: There are cases where importing pytorch3d seems to fail (internally at Meta) because of a clash between the builtin types module and ours, so rename ours.

Reviewed By: patricklabatut

Differential Revision: D34426817

fbshipit-source-id: f175448db6a4967a9a3f7bb6f595aad2ffb36455

Summary:
Run the circleci tests with a non depracated circleci image. Small fix for PyTorch 1.7.
We no longer need to manually install nvidia-docker or the CUDA driver.

Reviewed By: patricklabatut

Differential Revision: D34426816

fbshipit-source-id: d6c67bfb0ff86dff8d8f7fe7b8801657c2e80030

Summary:
# Changelist
- `matrix_to_axis_angle` was declared in `pytorch3d/transforms/rotation_conversions.py` but never exported from the `__init__` file.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1085

Reviewed By: patricklabatut

Differential Revision: D34379935

Pulled By: bottler

fbshipit-source-id: 993c12a176630f91d0f107f298f458b2b35032e5