GitLab

Summary:
generic_model_args no longer exists. Update some references to it, mostly in doc.

This fixes the testing of all the yaml files in test_forward pass.

Reviewed By: shapovalov

Differential Revision: D38789202

fbshipit-source-id: f11417efe772d7f86368b3598aa66c52b1309dbf

Reviewed By: shapovalov

Differential Revision: D38794764

fbshipit-source-id: 140c8a935d760bab8569d903cc52ac3dd73cd553

Summary: Reasonable to expect bool indexing.

Reviewed By: bottler, kjchalup

Differential Revision: D38741446

fbshipit-source-id: 22b607bf13110043c5624196c66ca1484fdbce6c

Summary: Previously, "psnr" was evaluated between the masked g.t. image and the render. To avoid confusion, "psnr" is now renamed to "psnr_masked".

Reviewed By: bottler

Differential Revision: D38707511

fbshipit-source-id: 8ee881ab1a05453d6692dde9782333a47d8c1234

Summary: Adds additional source views to the eval batches for evaluating many-view models on CO3D Challenge

Reviewed By: bottler

Differential Revision: D38705904

fbshipit-source-id: cf7d00dc7db926fbd1656dd97a729674e9ff5adb

Summary: Reports also the PSNR between the unmasked G.T. image and the render.

Reviewed By: bottler

Differential Revision: D38655943

fbshipit-source-id: 1603a2d02116ea1ce037e5530abe1afc65a2ba93

Summary:
LLFF (and most/all non-synth datasets) will have no background/foreground distinction. Add support for data with no fg mask.

Also, we had a bug in stats loading, like this:
  * Load stats
  * One of the stats has a history of length 0
  * That's fine, e.g. maybe it's fg_error but the dataset has no notion of fg/bg. So leave it as len 0
  * Check whether all the stats have the same history length as an arbitrarily chosen "reference-stat"
  * Ooops the reference-stat happened to be the stat with length 0
  * assert (legit_stat_len == reference_stat_len (=0)) ---> failed assert

Also some minor fixes (from Jeremy's other diff) to support LLFF

Reviewed By: davnov134

Differential Revision: D38475272

fbshipit-source-id: 5b35ac86d1d5239759f537621f41a3aa4eb3bd68

Summary: remove n_instances==0 special case, standardise args for GlobalEncoderBase's forward.

Reviewed By: shapovalov

Differential Revision: D37817340

fbshipit-source-id: 0aac5fbc7c336d09be9d412cffff5712bda27290

Summary: continued - avoid duplicate inputs

Reviewed By: davnov134

Differential Revision: D38248827

fbshipit-source-id: 91ed398e304496a936f66e7a70ab3d189eeb5c70

Summary: Don't copy from one part of config to another, rather do the copy within GenericModel.

Reviewed By: davnov134

Differential Revision: D38248828

fbshipit-source-id: ff8af985c37ea1f7df9e0aa0a45a58df34c3f893

Summary: Made the config system call open_dict when it calls the tweak function.

Reviewed By: shapovalov

Differential Revision: D38315334

fbshipit-source-id: 5924a92d8d0bf399bbf3788247f81fc990e265e7

Summary:
Stats are logically connected to the training loop, not to the model. Hence, moving to the training loop.

Also removing resume_epoch from OptimizerFactory in favor of a single place - ModelFactory. This removes the need for config consistency checks etc.

Reviewed By: kjchalup

Differential Revision: D38313475

fbshipit-source-id: a1d188a63e28459df381ff98ad8acdcdb14887b7

Summary: Simple DataLoaderMapProvider instance

Reviewed By: davnov134

Differential Revision: D38326719

fbshipit-source-id: 58556833e76fae5790d25a59bea0aac4ce046bf1

Summary:
Added _NEED_CONTROL
 to JsonIndexDatasetMapProviderV2 and made dataset_tweak_args use it.

Reviewed By: bottler

Differential Revision: D38313914

fbshipit-source-id: 529847571065dfba995b609a66737bd91e002cfe

Summary: Only import it if you ask for it.

Reviewed By: kjchalup

Differential Revision: D38327167

fbshipit-source-id: 3f05231f26eda582a63afc71b669996342b0c6f9

Summary: Make a dummy single-scene dataset using the code from generate_cow_renders (used in existing NeRF tutorials)

Reviewed By: kjchalup

Differential Revision: D38116910

fbshipit-source-id: 8db6df7098aa221c81d392e5cd21b0e67f65bd70

Summary:
This is an internal change in the config systen. It allows redefining a pluggable implementation with new default values. This is useful in notebooks / interactive use. For example, this now works.

        class A(ReplaceableBase):
            pass

        registry.register
        class B(A):
            i: int = 4

        class C(Configurable):
            a: A
            a_class_type: str = "B"

            def __post_init__(self):
                run_auto_creation(self)

        expand_args_fields(C)

        registry.register
        class B(A):
            i: int = 5

        c = C()

        assert c.a.i == 5

Reviewed By: shapovalov

Differential Revision: D38219371

fbshipit-source-id: 72911a9bd3426d3359cf8802cc016fc7f6d7713b

Summary:
Adding MeshRasterizerOpenGL, a faster alternative to MeshRasterizer. The new rasterizer follows the ideas from "Differentiable Surface Rendering via non-Differentiable Sampling".

The new rasterizer 20x faster on a 2M face mesh (try pose optimization on Nefertiti from https://www.cs.cmu.edu/~kmcrane/Projects/ModelRepository/!). The larger the mesh, the larger the speedup.

There are two main disadvantages:
* The new rasterizer works with an OpenGL backend, so requires pycuda.gl and pyopengl installed (though we avoided writing any C++ code, everything is in Python!)
* The new rasterizer is non-differentiable. However, you can still differentiate the rendering function if you use if with the new SplatterPhongShader which we recently added to PyTorch3D (see the original paper cited above).

Reviewed By: patricklabatut, jcjohnson

Differential Revision: D37698816

fbshipit-source-id: 54d120639d3cb001f096237807e54aced0acda25

Summary: Needed to properly change devices during OpenGL rasterization.

Reviewed By: jcjohnson

Differential Revision: D37698568

fbshipit-source-id: 38968149d577322e662d3b5d04880204b0a7be29

Summary:
EGLContext is a utility to render with OpenGL without an attached display (that is, without a monitor).

DeviceContextManager allows us to avoid unnecessary context creations and releases. See docstrings for more info.

Reviewed By: jcjohnson

Differential Revision: D36562551

fbshipit-source-id: eb0d2a2f85555ee110e203d435a44ad243281d2c

Summary: Avoid calculating all_train_cameras before it is needed, because it is slow in some datasets.

Reviewed By: shapovalov

Differential Revision: D38037157

fbshipit-source-id: 95461226655cde2626b680661951ab17ebb0ec75

Summary:
X-link: https://github.com/fairinternal/pytorch3d/pull/39

Blender and LLFF cameras were sending screen space focal length and principal point to a camera init function expecting NDC

Reviewed By: shapovalov

Differential Revision: D37788686

fbshipit-source-id: 2ddf7436248bc0d174eceb04c288b93858138582

Summary:
EPnP fails the test when the number of points is below 6. As suggested, quadratic option is in theory to deal with as few as 4 points (so num_pts_thresh=3 is set). And when num_pts > num_pts_thresh=4, skip_q is False.

To avoid bumping num_pts_thresh while passing all the original tests, check_output is set to False when num_pts < 6, similar to the logic in Line 123-127.  It makes sure that the algo doesn't crash.

Reviewed By: shapovalov

Differential Revision: D37804438

fbshipit-source-id: 74576d63a9553e25e3ec344677edb6912b5f9354

Summary: Fixing comments on D37592429 (https://github.com/facebookresearch/pytorch3d/commit/0dce883241ae638b9fa824f34fca9590d5f0782c)

Reviewed By: shapovalov

Differential Revision: D37752367

fbshipit-source-id: 40aa7ee4dc0c5b8b7a84a09d13a3933a9e3afedd

Summary:
This fixes a indexing bug in HardDepthShader and adds proper unit tests for both of the DepthShaders. This bug was introduced when updating the shader sizes and discovered when I switched my local model onto pytorch3d trunk instead of the patched copy.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1252

Test Plan:
Unit test + custom model code

```
pytest tests/test_shader.py
```

![image](https://user-images.githubusercontent.com/909104/178397456-f478d0e0-9f6c-467a-a85b-adb4c47adfee.png)

Reviewed By: bottler

Differential Revision: D37775767

Pulled By: d4l3k

fbshipit-source-id: 5f001903985976d7067d1fa0a3102d602790e3e8

renderer: add support for rendering high dimensional textures for classification/segmentation use cases (#1248)

Summary:
For 3D segmentation problems it's really useful to be able to train the models from multiple viewpoints using Pytorch3D as the renderer. Currently due to hardcoded assumptions in a few spots the mesh renderer only supports rendering RGB (3 dimensional) data. You can encode the classification information as 3 channel data but if you have more than 3 classes you're out of luck.

This relaxes the assumptions to make rendering semantic classes work with `HardFlatShader` and `AmbientLights` with no diffusion/specular. The other shaders/lights don't make any sense for classification since they mutate the texture values in some way.

This only requires changes in `Materials` and `AmbientLights`. The bulk of the code is the unit test.

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1248

Test Plan: Added unit test that renders a 5 dimensional texture and compare dimensions 2-5 to a stored picture.

Reviewed By: bottler

Differential Revision: D37764610

Pulled By: d4l3k

fbshipit-source-id: 031895724d9318a6f6bab5b31055bb3f438176a5

Summary: remove erroneous RandomDataLoaderMapProvider

Reviewed By: davnov134

Differential Revision: D37751116

fbshipit-source-id: cf3b555dc1e6304425914d1522b4f70407b498bf

Summary: A new version of json index dataset provider supporting CO3Dv2

Reviewed By: shapovalov

Differential Revision: D37690918

fbshipit-source-id: bf2d5fc9d0f1220259e08661dafc69cdbe6b7f94

Summary:
Implements several changes needed for the CO3Dv2 release:
- FrameData contains crop_bbox_xywh which defines the outline of the image crop corresponding to the image-shaped tensors in FrameData
- revised the definition of a bounding box inside JsonDatasetIndex: bbox_xyxy is [xmin, ymin, xmax, ymax], where xmax, ymax are not inclusive; bbox_xywh = [xmin, ymain, xmax-xmin, ymax-ymin]
- is_filtered for detecting whether the entries of the dataset were somehow filtered
- seq_frame_index_to_dataset_index allows to skip entries that are not present in the dataset

Reviewed By: shapovalov

Differential Revision: D37687547

fbshipit-source-id: 7842756b0517878cc0964fc0935d3c0769454d78

Summary: As part of removing Task, make the dataset code generate the source cameras for itself. There's a small optimization available here, in that the JsonIndexDataset could avoid loading images.

Reviewed By: shapovalov

Differential Revision: D37313423

fbshipit-source-id: 3e5e0b2aabbf9cc51f10547a3523e98c72ad8755

Summary: Add facilities for dataloading non-sequential scenes.

Reviewed By: shapovalov

Differential Revision: D37291277

fbshipit-source-id: 0a33e3727b44c4f0cba3a2abe9b12f40d2a20447

Summary: Refactors autodecoders. Tests pass.

Reviewed By: bottler

Differential Revision: D37592429

fbshipit-source-id: 8f5c9eac254e1fdf0704d5ec5f69eb42f6225113

Summary:
Make ViewMetrics easy to replace by putting them into an OmegaConf dataclass.

Also, re-word a few variable names and fix minor TODOs.

Reviewed By: bottler

Differential Revision: D37327157

fbshipit-source-id: 78d8e39bbb3548b952f10abbe05688409fb987cc

Summary: After landing https://github.com/pytorch/pytorch/pull/69607, that made it an error to use indexing with `cpu_tensor[cuda_indices]`. There was one outstanding test in fbcode that incorrectly used indexing in that way, which is fixed here

Reviewed By: bottler, osalpekar

Differential Revision: D37128838

fbshipit-source-id: 611b6f717b5b5d89fa61fd9ebeb513ad7e65a656

Summary:
David had his code crashed when using frame_annot["meta"] dictionary. Turns out we had a typo.
The tests were passing by chance since all the keys were single-character strings.

Reviewed By: bottler

Differential Revision: D37503987

fbshipit-source-id: c12b0df21116cfbbc4675a0182b9b9e6d62bad2e

Summary:
X-link: https://github.com/fairinternal/pytorch3d/pull/36

This adds two shaders for rendering depth maps for meshes. This is useful for structure from motion applications that learn depths based off of camera pair disparities.

There's two shaders, one hard which just returns the distances and then a second that does a cumsum on the probabilities of the points with a weighted sum. Areas that don't have any z faces are set to the zfar distance.

Output from this renderer is `[N, H, W]` since it's just depth no need for channels.

I haven't tested this in an ML model yet just in a notebook.

hard:
![hardzshader](https://user-images.githubusercontent.com/909104/170190363-ef662c97-0bd2-488c-8675-0557a3c7dd06.png)

soft:
![softzshader](https://user-images.githubusercontent.com/909104/170190365-65b08cd7-0c49-4119-803e-d33c1d8c676e.png)

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1208

Reviewed By: bottler

Differential Revision: D36682194

Pulled By: d4l3k

fbshipit-source-id: 5d4e10c6fb0fff5427be4ddd3bd76305a7ccc1e2

Summary: OmegaConf 2.2.2 doesn't like heterogenous tuples or Sequence or Set members. Workaround this.

Reviewed By: shapovalov

Differential Revision: D37278736

fbshipit-source-id: 123e6657947f5b27514910e4074c92086a457a2a

Summary: small followup to D37172537 (https://github.com/facebookresearch/pytorch3d/commit/cba26506b6fe8a98695f50673cb20d9597d87551) and D37209012 (https://github.com/facebookresearch/pytorch3d/commit/81d63c63823e146e74d7be367d19314ab16d6815): changing default #harmonics and improving a test

Reviewed By: shapovalov

Differential Revision: D37412357

fbshipit-source-id: 1af1005a129425fd24fa6dd213d69c71632099a0

Summary: The blender synthetic dataset contains object masks in the alpha channel. Provide these in the corresponding dataset.

Reviewed By: shapovalov

Differential Revision: D37344380

fbshipit-source-id: 3ddacad9d667c0fa0ae5a61fb1d2ffc806c9abf3

Summary: Images were coming out in the wrong format.

Reviewed By: shapovalov

Differential Revision: D37291278

fbshipit-source-id: c10871c37dd186982e7abf2071ac66ed583df2e6