- 18 Feb, 2020 1 commit
-
-
Junior Rojas authored
Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/54 Differential Revision: D19951851 Pulled By: gkioxari fbshipit-source-id: cf41d5806c761639d1efa42a633404b248486c30
-
- 14 Feb, 2020 1 commit
-
-
Nikhila Ravi authored
Summary: Ran `dev/linter.sh`. Reviewed By: bottler Differential Revision: D19761062 fbshipit-source-id: 1a49abe4a5f2bc7641b2b46e254aa77e6a48aa7d
-
- 13 Feb, 2020 2 commits
-
-
Georgia Gkioxari authored
Summary: Added cpu implementation for face areas normals. Moved test and bm to separate functions. ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- FACE_AREAS_NORMALS_2_100_300_False 196 268 2550 FACE_AREAS_NORMALS_2_100_300_True 106 179 4733 FACE_AREAS_NORMALS_2_100_3000_False 1447 1630 346 FACE_AREAS_NORMALS_2_100_3000_True 107 178 4674 FACE_AREAS_NORMALS_2_1000_300_False 201 309 2486 FACE_AREAS_NORMALS_2_1000_300_True 107 186 4673 FACE_AREAS_NORMALS_2_1000_3000_False 1451 1636 345 FACE_AREAS_NORMALS_2_1000_3000_True 107 186 4655 FACE_AREAS_NORMALS_10_100_300_False 767 918 653 FACE_AREAS_NORMALS_10_100_300_True 106 167 4712 FACE_AREAS_NORMALS_10_100_3000_False 7036 7754 72 FACE_AREAS_NORMALS_10_100_3000_True 113 164 4445 FACE_AREAS_NORMALS_10_1000_300_False 748 947 669 FACE_AREAS_NORMALS_10_1000_300_True 108 169 4638 FACE_AREAS_NORMALS_10_1000_3000_False 7069 7783 71 FACE_AREAS_NORMALS_10_1000_3000_True 108 172 4646 FACE_AREAS_NORMALS_32_100_300_False 2286 2496 219 FACE_AREAS_NORMALS_32_100_300_True 108 180 4631 FACE_AREAS_NORMALS_32_100_3000_False 23184 24369 22 FACE_AREAS_NORMALS_32_100_3000_True 159 213 3147 FACE_AREAS_NORMALS_32_1000_300_False 2414 2645 208 FACE_AREAS_NORMALS_32_1000_300_True 112 197 4480 FACE_AREAS_NORMALS_32_1000_3000_False 21687 22964 24 FACE_AREAS_NORMALS_32_1000_3000_True 141 211 3540 -------------------------------------------------------------------------------- Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- FACE_AREAS_NORMALS_TORCH_2_100_300_False 5465 5782 92 FACE_AREAS_NORMALS_TORCH_2_100_300_True 1198 1351 418 FACE_AREAS_NORMALS_TORCH_2_100_3000_False 48228 48869 11 FACE_AREAS_NORMALS_TORCH_2_100_3000_True 1186 1304 422 FACE_AREAS_NORMALS_TORCH_2_1000_300_False 5556 6097 90 FACE_AREAS_NORMALS_TORCH_2_1000_300_True 1200 1328 417 FACE_AREAS_NORMALS_TORCH_2_1000_3000_False 48683 50016 11 FACE_AREAS_NORMALS_TORCH_2_1000_3000_True 1185 1306 422 FACE_AREAS_NORMALS_TORCH_10_100_300_False 24215 25097 21 FACE_AREAS_NORMALS_TORCH_10_100_300_True 1150 1314 435 FACE_AREAS_NORMALS_TORCH_10_100_3000_False 232605 234952 3 FACE_AREAS_NORMALS_TORCH_10_100_3000_True 1193 1314 420 FACE_AREAS_NORMALS_TORCH_10_1000_300_False 24912 25343 21 FACE_AREAS_NORMALS_TORCH_10_1000_300_True 1216 1330 412 FACE_AREAS_NORMALS_TORCH_10_1000_3000_False 239907 241253 3 FACE_AREAS_NORMALS_TORCH_10_1000_3000_True 1226 1333 408 FACE_AREAS_NORMALS_TORCH_32_100_300_False 73991 75776 7 FACE_AREAS_NORMALS_TORCH_32_100_300_True 1193 1339 420 FACE_AREAS_NORMALS_TORCH_32_100_3000_False 728932 728932 1 FACE_AREAS_NORMALS_TORCH_32_100_3000_True 1186 1359 422 FACE_AREAS_NORMALS_TORCH_32_1000_300_False 76385 79129 7 FACE_AREAS_NORMALS_TORCH_32_1000_300_True 1165 1310 430 FACE_AREAS_NORMALS_TORCH_32_1000_3000_False 753276 753276 1 FACE_AREAS_NORMALS_TORCH_32_1000_3000_True 1205 1340 415 -------------------------------------------------------------------------------- ``` Reviewed By: bottler, jcjohnson Differential Revision: D19864385 fbshipit-source-id: 3a87ae41a8e3ab5560febcb94961798f2e09dfb8
-
Jeremy Reizenstein authored
Summary: Create the textures and the Meshes object from OBJ files in a single call. There is functionality in OBJ files (like normals) which is ignored by this function. Reviewed By: gkioxari Differential Revision: D19691699 fbshipit-source-id: e26442ed80ff231b65b17d6c54c9d41e22b4e4a3
-
- 11 Feb, 2020 2 commits
-
-
Jeremy Reizenstein authored
Reviewed By: gkioxari Differential Revision: D19834684 fbshipit-source-id: 553dbf84d1062149b4915d313fc0f96eb047798c
-
Nikhila Ravi authored
Summary: Update all colab notebooks to: - Install pytorch3d using pip install from github. - Retrieve data using `wget`. I set the wget commands to save the files in the same directory structure as in the PyTorch3d repo so that the rest of the tutorial would work for running locally or on Colab. This should resolve the issues on GitHub with running the colab notebooks. Reviewed By: gkioxari Differential Revision: D19827450 fbshipit-source-id: d7b338597ddfd9a84c24592d4dccd274cae11d05
-
- 10 Feb, 2020 1 commit
-
-
uzkt authored
Summary: fixed target object data folder path './data/doplhin'-> './data/dolphin' Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/34 Differential Revision: D19815377 Pulled By: nikhilaravi fbshipit-source-id: ff17f6aef8d835b11d7803e912a311c7118b03fa
-
- 08 Feb, 2020 2 commits
-
-
Nikhila Ravi authored
Summary: Added if `WITH_CUDA` checks for points/mesh rasterization. If installing on cpu only then this causes `Undefined symbol` errors when trying to import pytorch3d. We had these checks for all the other cuda files but not the rasterization files. Thanks ppwwyyxx for the tip! Reviewed By: ppwwyyxx, gkioxari Differential Revision: D19801495 fbshipit-source-id: 20e7adccfdb33ac731c00a89414b2beaf0a35529
-
Yannick Soom authored
Summary: fixed small typo in deform_source_mesh_to_target_mesh.ipynb Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/24 Differential Revision: D19801629 Pulled By: nikhilaravi fbshipit-source-id: 59459f701e0a4c02e749a1b594ca77935fd037d1
-
- 07 Feb, 2020 3 commits
-
-
Ignacio López-Francos authored
Summary: the dot at the pip command was outside of the inline code formatting. I just moved the back tick after the dot. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/21 Differential Revision: D19791603 Pulled By: nikhilaravi fbshipit-source-id: 6b0bedd2a788aef0d9678f9c1c25354ada76a3f4
-
frederikzt authored
Summary: The missing single quote makes you unable to directly cope the line if code into Colab Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/23 Differential Revision: D19791643 Pulled By: nikhilaravi fbshipit-source-id: 2aa043ad4163eb7146c7b8b00bd8846ae61d8009
-
Jeremy Reizenstein authored
Summary: Make RasterizationSettings be a NamedTuple instead of a dataclass. This makes the mesh renderer work with python 3.6. Reviewed By: nikhilaravi Differential Revision: D19769924 fbshipit-source-id: db839f3506dda7d3344fb8a101fa75bdf139ce39
-
- 05 Feb, 2020 3 commits
-
-
Nikhila Ravi authored
Summary: Updated media queries for website on mobile. Reviewed By: gkioxari Differential Revision: D19745526 fbshipit-source-id: a8dc25fcc04726056231d2e1ebeb581251be9324
-
Nikhila Ravi authored
Summary: A few minor updates to the website. - fix the color gradient on the homepage - fix unicode escape for the copyright symbol Reviewed By: gkioxari Differential Revision: D19744165 fbshipit-source-id: 31068bd0b408fe7b298e1f69d9998d64498e9d8c
-
Nikhila Ravi authored
Summary: Set up landing page, docs page, and html versions of the ipython notebook tutorials. Pull Request resolved: https://github.com/fairinternal/pytorch3d/pull/11 Reviewed By: gkioxari Differential Revision: D19730380 Pulled By: nikhilaravi fbshipit-source-id: 5df8d3f2ac2f8dce4d51f5d14fc336508c2fd0ea
-
- 03 Feb, 2020 1 commit
-
-
Justin Johnson authored
Summary: Adds a CPU implementation for `pytorch3d.ops.nn_points_idx`. Also renames the associated C++ and CUDA functions to use `AllCaps` names used in other C++ / CUDA code. Reviewed By: gkioxari Differential Revision: D19670491 fbshipit-source-id: 1b6409404025bf05e6a93f5d847e35afc9062f05
-
- 31 Jan, 2020 2 commits
-
-
Haoqi Fan authored
Reviewed By: bottler, wanyenlo Differential Revision: D19658045 fbshipit-source-id: a623a81c1ed1fa4054ea55bf06a2926e297b7966
-
Georgia Gkioxari authored
Summary: Add flag for loading textures Reviewed By: nikhilaravi Differential Revision: D19664437 fbshipit-source-id: 3cc4e6179df9b7e24efff9e7da3b164253f1d775
-
- 27 Jan, 2020 1 commit
-
-
Jeremy Reizenstein authored
Summary: This makes sure circle ci builds work with cuda even on machines with no gpu. Reviewed By: gkioxari Differential Revision: D19543957 fbshipit-source-id: 9cbfcd4fca22ebe89434ffa71c25d75dd18d2eb6
-
- 24 Jan, 2020 4 commits
-
-
Yun Chen authored
Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/8 Differential Revision: D19556466 Pulled By: nikhilaravi fbshipit-source-id: 26aa361882b688e7cd159e0d7d8cfad37d0049c1
-
Yun Chen authored
Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/7 Differential Revision: D19556384 Pulled By: nikhilaravi fbshipit-source-id: 4bd93a3bff92cbba78600bda703a19fd1c663109
-
Nikhila Ravi authored
Summary: We need to install pytorch3d in RTD. Update requirements.txt accordingly. Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/6 Reviewed By: gkioxari Differential Revision: D19549348 Pulled By: nikhilaravi fbshipit-source-id: d8d6efe0af9c0d4c7cc6f7662d392f5b3bc16a8c
-
Nikhila Ravi authored
Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/5 Reviewed By: gkioxari Differential Revision: D19548185 Pulled By: nikhilaravi fbshipit-source-id: edc825d483a29f1a3311d46b4f349a6bc330c085
-
- 23 Jan, 2020 2 commits
-
-
Nikhila Ravi authored
Summary: Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/4 Differential Revision: D19546949 Pulled By: nikhilaravi fbshipit-source-id: ce30785322a60c408fd6aa2f1cd3eb5d07015c7b
-
facebook-github-bot authored
fbshipit-source-id: ad58e416e3ceeca85fae0583308968d04e78fe0d
-