GitLab

Summary:
Added a suit of functions and code additions to experimental_gltf_io.py file to enable saving Meshes in TexturesVertex format into .glb file.
Also added a test to tets_io_gltf.py to check the functionality with the test described in Test Plane.

Reviewed By: bottler

Differential Revision: D44969144

fbshipit-source-id: 9ce815a1584b510442fa36cc4dbc8d41cc3786d5

Summary: Remove the need of tuple and reversed in the raysampling xy_grid computation

Reviewed By: bottler

Differential Revision: D45269342

fbshipit-source-id: d0e4c0923b9a2cca674b35e8d64862043a0eab3b

Summary:
Moving SQL dataset to PyTorch3D. It has been extensively tested in pixar_replay.

It requires SQLAlchemy 2.0, which is not supported in fbcode. So I exclude the sources and tests that depend on it from buck TARGETS.

Reviewed By: bottler

Differential Revision: D45086611

fbshipit-source-id: 0285f03e5824c0478c70ad13731525bb5ec7deef

Summary:
We currently support caching bounding boxes in MaskAnnotation. If present, they are not re-computed from the mask. However, the masks need to be loaded for the bbox to be set.

This diff fixes that. Even if load_masks / load_blobs are unset, the bounding box can be picked up from the metadata.

Reviewed By: bottler

Differential Revision: D45144918

fbshipit-source-id: 8a2e2c115e96070b6fcdc29cbe57e1cee606ddcd

Summary: The code does not crash if depth map/mask are not given.

Reviewed By: bottler

Differential Revision: D45082985

fbshipit-source-id: 3610d8beb4ac897fbbe52f56a6dd012a6365b89b

Summary:
The pattern
```
X.Y if hasattr(X, "Y") else Z
```
can be replaced with
```
getattr(X, "Y", Z)
```

The [getattr](https://www.w3schools.com/python/ref_func_getattr.asp) function gives more succinct code than the [hasattr](https://www.w3schools.com/python/ref_func_hasattr.asp) function. Please use it when appropriate.

**This diff is very low risk. Green tests indicate that you can safely Accept & Ship.**

Reviewed By: bottler

Differential Revision: D44886893

fbshipit-source-id: 86ba23e837217e1ebd64bf8e27d286257894839e

Differential Revision: D44881859

fbshipit-source-id: 4ed410724a14d580f811c1288f51a71ce8fb0c9a

Summary: update version number

Reviewed By: davidsonic

Differential Revision: D44343297

fbshipit-source-id: 763a25fbe0c880e8b7ad851b8e4b57787e449cab

Summary: PyTorch 2.0 now supported

Reviewed By: davidsonic

Differential Revision: D44343298

fbshipit-source-id: c81556dc872141e692a97845da0fb50fe82f62da

Summary:
Allow pytorch2.0 download:
```
sed -i 's/startswith(\\"1.13.\\")/startswith\(\(\\"1.13.\\", \\"2.0.\\"\)\)/' *b
```

Remove lines which download and install CUB:
```
sed -i.bak '/1.10\.0/d' *b
rm *.bak
```

Reviewed By: davidsonic

Differential Revision: D44343299

fbshipit-source-id: e8399b5dd10068c717178ba9ffb0630bacca3253

Summary:
extracted blob loader
added documentation for blob_loader
did some refactoring on fields
for detailed steps and discussions see:
https://github.com/facebookresearch/pytorch3d/pull/1463
https://github.com/fairinternal/pixar_replay/pull/160

Reviewed By: bottler

Differential Revision: D44061728

fbshipit-source-id: eefb21e9679003045d73729f96e6a93a1d4d2d51

Summary: Provide an extension point pre_expand to let a configurable class A make sure another class B is registered before A is expanded. This reduces top level imports.

Reviewed By: bottler

Differential Revision: D44504122

fbshipit-source-id: c418bebbe6d33862d239be592d9751378eee3a62

Summary:
Introduces the OverfitModel for NeRF-style training with overfitting to one scene.
It is a specific case of GenericModel. It has been disentangle to ease usage.

## General modification

1. Modularize a minimum GenericModel to introduce OverfitModel
2. Introduce OverfitModel and ensure through unit testing that it behaves like GenericModel.

## Modularization

The following methods have been extracted from GenericModel to allow modularity with ManyViewModel:
- get_objective is now a call to weighted_sum_losses
- log_loss_weights
- prepare_inputs

The generic methods have been moved to an utils.py file.

Simplify the code to introduce OverfitModel.

Private methods like chunk_generator are now public and can now be used by ManyViewModel.

Reviewed By: shapovalov

Differential Revision: D43771992

fbshipit-source-id: 6102aeb21c7fdd56aa2ff9cd1dd23fd9fbf26315

Summary: For safety checks, make inplace forward operations in cuda and c++ call increment_version.

Reviewed By: davidsonic

Differential Revision: D44302504

fbshipit-source-id: 6ff62251e352d6778cb54399e2e11459e16e77ba

Summary:
Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1480

Nightly builds with PyTorch 2.0.

Reviewed By: shapovalov

Differential Revision: D44135997

fbshipit-source-id: 12b363e2eadbda7a9b6ba9d8db376f41b96d551c

Differential Revision: D44182699

fbshipit-source-id: bdc5f495eaaee8ce461b91271d476d7b3ec3f8a2

Summary:
spelling errors in io.md

see https://github.com/facebookresearch/pytorch3d/discussions/1450

Reviewed By: davidsonic

Differential Revision: D43269978

fbshipit-source-id: 4bbe1f00bdeda4c51b7620e7b9cc065840303530

Summary: New function

Reviewed By: davidsonic

Differential Revision: D42776590

fbshipit-source-id: 2a6e73480bcf2d1749f86bcb22d1942e3e8d3167

Summary: - Replace all the relative imports for generic models to absolute import: (from . import y => from pytorch3.x import y)

Reviewed By: shapovalov

Differential Revision: D43620682

fbshipit-source-id: 937318b339b5020d17b511a891c7b000ff659328

Reviewed By: bottler

Differential Revision: D43432438

fbshipit-source-id: 58159b2febb67febb533511eb2d1f47d40dad032

Differential Revision: D43044534

fbshipit-source-id: dc841b6704ccd562f5a40e7b2834e26063a9f7ae

Differential Revision: D42947615

fbshipit-source-id: 47b078fdf68567220e15993ab643f85771b0d340

Summary: see title

Reviewed By: bottler

Differential Revision: D42920739

fbshipit-source-id: 87f3d052657880b2ef58a1219bb7d4f283ab0830

Summary: D42760349 (https://github.com/facebookresearch/pytorch3d/commit/9540c29023c2b6bb53e5a26a5e7a9d34ce88e9b1) (make Module.__init__ automatic) didn't account properly for inheritance.

Reviewed By: shapovalov

Differential Revision: D42834466

fbshipit-source-id: 53ee4c788985c1678ad905c06ccf12b2b41361e9

Summary: Indexing with a big matrix now fails with a ValueError, possibly because of pytorch improvements. Remove the testcase for it.

Reviewed By: davidsonic

Differential Revision: D42609741

fbshipit-source-id: 0a5a6632ed199cb942bfc4cc4ed347b72e491125

Summary:
Aligning the logic with the official CO3Dv2 evaluation: https://github.com/facebookresearch/co3d/blob/92283c43688c3be685eea35f2eaf3ce58b5bbf0b/co3d/dataset/utils.py#L7

This will make the evaluator work with the datasets that do not define known/unseen subsets.

Reviewed By: bottler

Differential Revision: D42803136

fbshipit-source-id: cfac389eab010c32d2e33b40fc7f6ed845c327ef

Summary: If a configurable class inherits torch.nn.Module and is instantiated, automatically call `torch.nn.Module.__init__` on it before doing anything else.

Reviewed By: shapovalov

Differential Revision: D42760349

fbshipit-source-id: 409894911a4252b7987e1fd218ee9ecefbec8e62

Reviewed By: shapovalov

Differential Revision: D42780711

fbshipit-source-id: 075fcae5097147b782f7ffc935f5430b824f58fd

Summary: Pull Request resolved: https://github.com/fairinternal/pytorch3d/pull/43

Reviewed By: bottler

Differential Revision: D42791756

Pulled By: nikhilaravi

fbshipit-source-id: 498399c1ce30bb095579c4d66b6314a6aa846df3

Differential Revision: D42775736

fbshipit-source-id: 8425305cd99d50ebc155502d56c0deeee1d078ab

Summary: ChainDataset is iterable, and it toes not go along with a custom batch sampler.

Reviewed By: bottler

Differential Revision: D42742315

fbshipit-source-id: 40a715c8d24abe72cb2777634247d7467f628564

Summary: For the new API, filtering iterators over sequences by subsets is quite helpful. The change is backwards compatible.

Reviewed By: bottler

Differential Revision: D42739669

fbshipit-source-id: d150a404aeaf42fd04a81304c63a4cba203f897d

Summary:
V2 dataset does not have the concept of known/unseen frames. Test-time conditining is done with train-set frames, which violates the previous check.

Also fixing a corner case in VideoWriter.

Reviewed By: bottler

Differential Revision: D42706976

fbshipit-source-id: d43be3dd3060d18cb9f46d5dcf6252d9f084110f

Summary:
Fixes some issues with RayBundle plotting:
- allows plotting raybundles on gpu
- view -> reshape since we do not require contiguous raybundle tensors as input

Reviewed By: bottler, shapovalov

Differential Revision: D42665923

fbshipit-source-id: e9c6c7810428365dca4cb5ec80ef15ff28644163

Summary: docstring and shape fix

Reviewed By: shapovalov

Differential Revision: D42609661

fbshipit-source-id: fd50234872ad61b5452821eeb89d51344f70c957

Summary: We don’t see much value in reporting metrics by camera difficulty while supporting that in new datasets is quite painful, hence deprecating training cameras in the data API and ignoring in evaluation.

Reviewed By: bottler

Differential Revision: D42678879

fbshipit-source-id: aad511f6cb2ca82745f31c19594e1d80594b61d7

Summary: Allows to send kwargs to render_flyaround from visualize_reconstruction

Reviewed By: bottler, shapovalov

Differential Revision: D41157683

fbshipit-source-id: 74d8d7de4e991a31b14e72d76de5efdb8ab4b2c5

Summary:
The file [rasterizer.py](https://github.com/facebookresearch/pytorch3d/blob/de3a474d2b9e0f5d4a77c82106a4a8e7853a4e07/pytorch3d/renderer/mesh/rasterizer.py#L201) contains a duplicate line before the check if the projection_transform exists. This causes an exception in the case that a projection transform matrix is already provided. The corresponding lines should be (and are already) in the else case of the if-statement.

Removing these lines fixes the bug and produces the desired behavior.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1421

Reviewed By: shapovalov

Differential Revision: D42450999

Pulled By: bottler

fbshipit-source-id: f7464e87ec9ff8768455656324b0b008132c8a54

Reviewed By: shapovalov

Differential Revision: D42545069

fbshipit-source-id: e25fb4049dcebd715df43bab3ce813ecb5f85abe

Summary: Use IndexError so that a camera object is an iterable

Reviewed By: shapovalov

Differential Revision: D42312021

fbshipit-source-id: 67c417d5f1398e8b30a6944468eda057b4ceb444