fbcode/vision/fair/pytorch3d/pytorch3d/transforms/rotation_conversions.py

Reviewed By: bottler

Differential Revision: D93712828

fbshipit-source-id: 3465af450104bb1e5f491e3c0ee0259698cf8ceb

.circleci/config.yml

@@ -162,90 +162,6 @@ workflows:
     jobs:
       # - main:
       #     context: DOCKERHUB_TOKEN
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
-          context: DOCKERHUB_TOKEN
-          cu_version: cu113
-          name: linux_conda_py38_cu113_pyt1120
-          python_version: '3.8'
-          pytorch_version: 1.12.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py38_cu116_pyt1120
-          python_version: '3.8'
-          pytorch_version: 1.12.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
-          context: DOCKERHUB_TOKEN
-          cu_version: cu113
-          name: linux_conda_py38_cu113_pyt1121
-          python_version: '3.8'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py38_cu116_pyt1121
-          python_version: '3.8'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py38_cu116_pyt1130
-          python_version: '3.8'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py38_cu117_pyt1130
-          python_version: '3.8'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py38_cu116_pyt1131
-          python_version: '3.8'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py38_cu117_pyt1131
-          python_version: '3.8'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py38_cu117_pyt200
-          python_version: '3.8'
-          pytorch_version: 2.0.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda118
-          context: DOCKERHUB_TOKEN
-          cu_version: cu118
-          name: linux_conda_py38_cu118_pyt200
-          python_version: '3.8'
-          pytorch_version: 2.0.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py38_cu117_pyt201
-          python_version: '3.8'
-          pytorch_version: 2.0.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda118
-          context: DOCKERHUB_TOKEN
-          cu_version: cu118
-          name: linux_conda_py38_cu118_pyt201
-          python_version: '3.8'
-          pytorch_version: 2.0.1
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
@@ -261,89 +177,103 @@ workflows:
           python_version: '3.8'
           pytorch_version: 2.1.0
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
+          conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
-          cu_version: cu113
+          cu_version: cu118
-          name: linux_conda_py39_cu113_pyt1120
+          name: linux_conda_py38_cu118_pyt211
-          python_version: '3.9'
+          python_version: '3.8'
-          pytorch_version: 1.12.0
+          pytorch_version: 2.1.1
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
+          conda_docker_image: pytorch/conda-builder:cuda121
           context: DOCKERHUB_TOKEN
-          cu_version: cu116
+          cu_version: cu121
-          name: linux_conda_py39_cu116_pyt1120
+          name: linux_conda_py38_cu121_pyt211
-          python_version: '3.9'
+          python_version: '3.8'
-          pytorch_version: 1.12.0
+          pytorch_version: 2.1.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
-          context: DOCKERHUB_TOKEN
-          cu_version: cu113
-          name: linux_conda_py39_cu113_pyt1121
-          python_version: '3.9'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py39_cu116_pyt1121
-          python_version: '3.9'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py39_cu116_pyt1130
-          python_version: '3.9'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py39_cu117_pyt1130
-          python_version: '3.9'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py39_cu116_pyt1131
-          python_version: '3.9'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py39_cu117_pyt1131
-          python_version: '3.9'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py39_cu117_pyt200
-          python_version: '3.9'
-          pytorch_version: 2.0.0
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
           cu_version: cu118
-          name: linux_conda_py39_cu118_pyt200
+          name: linux_conda_py38_cu118_pyt212
-          python_version: '3.9'
+          python_version: '3.8'
-          pytorch_version: 2.0.0
+          pytorch_version: 2.1.2
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
+          conda_docker_image: pytorch/conda-builder:cuda121
           context: DOCKERHUB_TOKEN
-          cu_version: cu117
+          cu_version: cu121
-          name: linux_conda_py39_cu117_pyt201
+          name: linux_conda_py38_cu121_pyt212
-          python_version: '3.9'
+          python_version: '3.8'
-          pytorch_version: 2.0.1
+          pytorch_version: 2.1.2
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
           cu_version: cu118
-          name: linux_conda_py39_cu118_pyt201
+          name: linux_conda_py38_cu118_pyt220
-          python_version: '3.9'
+          python_version: '3.8'
-          pytorch_version: 2.0.1
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py38_cu121_pyt220
+          python_version: '3.8'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py38_cu118_pyt222
+          python_version: '3.8'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py38_cu121_pyt222
+          python_version: '3.8'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py38_cu118_pyt231
+          python_version: '3.8'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py38_cu121_pyt231
+          python_version: '3.8'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py38_cu118_pyt240
+          python_version: '3.8'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py38_cu121_pyt240
+          python_version: '3.8'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py38_cu118_pyt241
+          python_version: '3.8'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py38_cu121_pyt241
+          python_version: '3.8'
+          pytorch_version: 2.4.1
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
@@ -359,89 +289,103 @@ workflows:
           python_version: '3.9'
           pytorch_version: 2.1.0
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
+          conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
-          cu_version: cu113
+          cu_version: cu118
-          name: linux_conda_py310_cu113_pyt1120
+          name: linux_conda_py39_cu118_pyt211
-          python_version: '3.10'
+          python_version: '3.9'
-          pytorch_version: 1.12.0
+          pytorch_version: 2.1.1
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
+          conda_docker_image: pytorch/conda-builder:cuda121
           context: DOCKERHUB_TOKEN
-          cu_version: cu116
+          cu_version: cu121
-          name: linux_conda_py310_cu116_pyt1120
+          name: linux_conda_py39_cu121_pyt211
-          python_version: '3.10'
+          python_version: '3.9'
-          pytorch_version: 1.12.0
+          pytorch_version: 2.1.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda113
-          context: DOCKERHUB_TOKEN
-          cu_version: cu113
-          name: linux_conda_py310_cu113_pyt1121
-          python_version: '3.10'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py310_cu116_pyt1121
-          python_version: '3.10'
-          pytorch_version: 1.12.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py310_cu116_pyt1130
-          python_version: '3.10'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py310_cu117_pyt1130
-          python_version: '3.10'
-          pytorch_version: 1.13.0
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda116
-          context: DOCKERHUB_TOKEN
-          cu_version: cu116
-          name: linux_conda_py310_cu116_pyt1131
-          python_version: '3.10'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py310_cu117_pyt1131
-          python_version: '3.10'
-          pytorch_version: 1.13.1
-      - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
-          context: DOCKERHUB_TOKEN
-          cu_version: cu117
-          name: linux_conda_py310_cu117_pyt200
-          python_version: '3.10'
-          pytorch_version: 2.0.0
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
           cu_version: cu118
-          name: linux_conda_py310_cu118_pyt200
+          name: linux_conda_py39_cu118_pyt212
-          python_version: '3.10'
+          python_version: '3.9'
-          pytorch_version: 2.0.0
+          pytorch_version: 2.1.2
       - binary_linux_conda:
-          conda_docker_image: pytorch/conda-builder:cuda117
+          conda_docker_image: pytorch/conda-builder:cuda121
           context: DOCKERHUB_TOKEN
-          cu_version: cu117
+          cu_version: cu121
-          name: linux_conda_py310_cu117_pyt201
+          name: linux_conda_py39_cu121_pyt212
-          python_version: '3.10'
+          python_version: '3.9'
-          pytorch_version: 2.0.1
+          pytorch_version: 2.1.2
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
           cu_version: cu118
-          name: linux_conda_py310_cu118_pyt201
+          name: linux_conda_py39_cu118_pyt220
-          python_version: '3.10'
+          python_version: '3.9'
-          pytorch_version: 2.0.1
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py39_cu121_pyt220
+          python_version: '3.9'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py39_cu118_pyt222
+          python_version: '3.9'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py39_cu121_pyt222
+          python_version: '3.9'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py39_cu118_pyt231
+          python_version: '3.9'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py39_cu121_pyt231
+          python_version: '3.9'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py39_cu118_pyt240
+          python_version: '3.9'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py39_cu121_pyt240
+          python_version: '3.9'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py39_cu118_pyt241
+          python_version: '3.9'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py39_cu121_pyt241
+          python_version: '3.9'
+          pytorch_version: 2.4.1
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
@@ -456,6 +400,104 @@ workflows:
           name: linux_conda_py310_cu121_pyt210
           python_version: '3.10'
           pytorch_version: 2.1.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt211
+          python_version: '3.10'
+          pytorch_version: 2.1.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt211
+          python_version: '3.10'
+          pytorch_version: 2.1.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt212
+          python_version: '3.10'
+          pytorch_version: 2.1.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt212
+          python_version: '3.10'
+          pytorch_version: 2.1.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt220
+          python_version: '3.10'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt220
+          python_version: '3.10'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt222
+          python_version: '3.10'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt222
+          python_version: '3.10'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt231
+          python_version: '3.10'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt231
+          python_version: '3.10'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt240
+          python_version: '3.10'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt240
+          python_version: '3.10'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py310_cu118_pyt241
+          python_version: '3.10'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py310_cu121_pyt241
+          python_version: '3.10'
+          pytorch_version: 2.4.1
       - binary_linux_conda:
           conda_docker_image: pytorch/conda-builder:cuda118
           context: DOCKERHUB_TOKEN
@@ -470,6 +512,174 @@ workflows:
           name: linux_conda_py311_cu121_pyt210
           python_version: '3.11'
           pytorch_version: 2.1.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt211
+          python_version: '3.11'
+          pytorch_version: 2.1.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt211
+          python_version: '3.11'
+          pytorch_version: 2.1.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt212
+          python_version: '3.11'
+          pytorch_version: 2.1.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt212
+          python_version: '3.11'
+          pytorch_version: 2.1.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt220
+          python_version: '3.11'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt220
+          python_version: '3.11'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt222
+          python_version: '3.11'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt222
+          python_version: '3.11'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt231
+          python_version: '3.11'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt231
+          python_version: '3.11'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt240
+          python_version: '3.11'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt240
+          python_version: '3.11'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py311_cu118_pyt241
+          python_version: '3.11'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py311_cu121_pyt241
+          python_version: '3.11'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py312_cu118_pyt220
+          python_version: '3.12'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py312_cu121_pyt220
+          python_version: '3.12'
+          pytorch_version: 2.2.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py312_cu118_pyt222
+          python_version: '3.12'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py312_cu121_pyt222
+          python_version: '3.12'
+          pytorch_version: 2.2.2
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py312_cu118_pyt231
+          python_version: '3.12'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py312_cu121_pyt231
+          python_version: '3.12'
+          pytorch_version: 2.3.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py312_cu118_pyt240
+          python_version: '3.12'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py312_cu121_pyt240
+          python_version: '3.12'
+          pytorch_version: 2.4.0
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda118
+          context: DOCKERHUB_TOKEN
+          cu_version: cu118
+          name: linux_conda_py312_cu118_pyt241
+          python_version: '3.12'
+          pytorch_version: 2.4.1
+      - binary_linux_conda:
+          conda_docker_image: pytorch/conda-builder:cuda121
+          context: DOCKERHUB_TOKEN
+          cu_version: cu121
+          name: linux_conda_py312_cu121_pyt241
+          python_version: '3.12'
+          pytorch_version: 2.4.1
       - binary_linux_conda_cuda:
           name: testrun_conda_cuda_py310_cu117_pyt201
           context: DOCKERHUB_TOKEN

.circleci/regenerate.py

@@ -19,19 +19,18 @@ from packaging import version
 # The CUDA versions which have pytorch conda packages available for linux for each
 # version of pytorch.
 CONDA_CUDA_VERSIONS = {
-    "1.12.0": ["cu113", "cu116"],
-    "1.12.1": ["cu113", "cu116"],
-    "1.13.0": ["cu116", "cu117"],
-    "1.13.1": ["cu116", "cu117"],
-    "2.0.0": ["cu117", "cu118"],
-    "2.0.1": ["cu117", "cu118"],
     "2.1.0": ["cu118", "cu121"],
+    "2.1.1": ["cu118", "cu121"],
+    "2.1.2": ["cu118", "cu121"],
+    "2.2.0": ["cu118", "cu121"],
+    "2.2.2": ["cu118", "cu121"],
+    "2.3.1": ["cu118", "cu121"],
+    "2.4.0": ["cu118", "cu121"],
+    "2.4.1": ["cu118", "cu121"],
 }
 
 
 def conda_docker_image_for_cuda(cuda_version):
-    if cuda_version in ("cu101", "cu102", "cu111"):
-        return None
     if len(cuda_version) != 5:
         raise ValueError("Unknown cuda version")
     return "pytorch/conda-builder:cuda" + cuda_version[2:]
@@ -52,12 +51,18 @@ def pytorch_versions_for_python(python_version):
             for i in CONDA_CUDA_VERSIONS
             if version.Version(i) >= version.Version("2.1.0")
         ]
+    if python_version == "3.12":
+        return [
+            i
+            for i in CONDA_CUDA_VERSIONS
+            if version.Version(i) >= version.Version("2.2.0")
+        ]
 
 
 def workflows(prefix="", filter_branch=None, upload=False, indentation=6):
     w = []
     for btype in ["conda"]:
-        for python_version in ["3.8", "3.9", "3.10", "3.11"]:
+        for python_version in ["3.8", "3.9", "3.10", "3.11", "3.12"]:
             for pytorch_version in pytorch_versions_for_python(python_version):
                 for cu_version in CONDA_CUDA_VERSIONS[pytorch_version]:
                     w += workflow_pair(
@@ -83,7 +88,6 @@ def workflow_pair(
     upload=False,
     filter_branch,
 ):
-
     w = []
     py = python_version.replace(".", "")
     pyt = pytorch_version.replace(".", "")
@@ -122,7 +126,6 @@ def generate_base_workflow(
     btype,
     filter_branch=None,
 ):
-
     d = {
         "name": base_workflow_name,
         "python_version": python_version,

.flake8

@@ -1,5 +1,8 @@
 [flake8]
-ignore = E203, E266, E501, W503, E221
+# B028 No explicit stacklevel argument found.
+# B907 'foo' is manually surrounded by quotes, consider using the `!r` conversion flag.
+# B905 `zip()` without an explicit `strict=` parameter.
+ignore = E203, E266, E501, W503, E221, B028, B905, B907
 max-line-length = 88
 max-complexity = 18
 select = B,C,E,F,W,T4,B9

.github/workflows/build.yml

@@ -0,0 +1,23 @@
+name: facebookresearch/pytorch3d/build_and_test
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+jobs:
+  binary_linux_conda_cuda:
+    runs-on: 4-core-ubuntu-gpu-t4
+    env:
+      PYTHON_VERSION: "3.12"
+      BUILD_VERSION: "${{ github.run_number }}"
+      PYTORCH_VERSION: "2.4.1"
+      CU_VERSION: "cu121"
+      JUST_TESTRUN: 1
+    steps:
+    - uses: actions/checkout@v4
+    - name: Build and run tests
+      run: |-
+        conda create --name env --yes --quiet conda-build
+        conda run --no-capture-output --name env python3 ./packaging/build_conda.py --use-conda-cuda

INSTALL.md

@@ -8,11 +8,10 @@
 The core library is written in PyTorch. Several components have underlying implementation in CUDA for improved performance. A subset of these components have CPU implementations in C++/PyTorch. It is advised to use PyTorch3D with GPU support in order to use all the features.
 
 - Linux or macOS or Windows
-- Python 3.8, 3.9 or 3.10
+- Python
-- PyTorch 1.12.0, 1.12.1, 1.13.0, 2.0.0, 2.0.1 or 2.1.0.
+- PyTorch 2.1.0, 2.1.1, 2.1.2, 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.3.1, 2.4.0 or 2.4.1.
 - torchvision that matches the PyTorch installation. You can install them together as explained at pytorch.org to make sure of this.
 - gcc & g++ ≥ 4.9
-- [fvcore](https://github.com/facebookresearch/fvcore)
 - [ioPath](https://github.com/facebookresearch/iopath)
 - If CUDA is to be used, use a version which is supported by the corresponding pytorch version and at least version 9.2.
 - If CUDA older than 11.7 is to be used and you are building from source, the CUB library must be available. We recommend version 1.10.0.
@@ -22,7 +21,7 @@ The runtime dependencies can be installed by running:
 conda create -n pytorch3d python=3.9
 conda activate pytorch3d
 conda install pytorch=1.13.0 torchvision pytorch-cuda=11.6 -c pytorch -c nvidia
-conda install -c fvcore -c iopath -c conda-forge fvcore iopath
+conda install -c iopath iopath
 ```
 
 For the CUB build time dependency, which you only need if you have CUDA older than 11.7, if you are using conda, you can continue with
@@ -49,6 +48,7 @@ For developing on top of PyTorch3D or contributing, you will need to run the lin
 - tdqm
 - jupyter
 - imageio
+- fvcore
 - plotly
 - opencv-python
 
@@ -59,6 +59,7 @@ conda install jupyter
 pip install scikit-image matplotlib imageio plotly opencv-python
 
 # Tests/Linting
+conda install -c fvcore -c conda-forge fvcore
 pip install black usort flake8 flake8-bugbear flake8-comprehensions
 ```
 
@@ -97,7 +98,7 @@ version_str="".join([
     torch.version.cuda.replace(".",""),
     f"_pyt{pyt_version_str}"
 ])
-!pip install fvcore iopath
+!pip install iopath
 !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html
 ```
 

README.md

@@ -146,6 +146,12 @@ If you are using the pulsar backend for sphere-rendering (the `PulsarPointRender
 
 Please see below for a timeline of the codebase updates in reverse chronological order. We are sharing updates on the releases as well as research projects which are built with PyTorch3D. The changelogs for the releases are available under [`Releases`](https://github.com/facebookresearch/pytorch3d/releases),  and the builds can be installed using `conda` as per the instructions in [INSTALL.md](INSTALL.md).
 
+**[Oct 31st 2023]:**   PyTorch3D [v0.7.5](https://github.com/facebookresearch/pytorch3d/releases/tag/v0.7.5) released.
+
+**[May 10th 2023]:**   PyTorch3D [v0.7.4](https://github.com/facebookresearch/pytorch3d/releases/tag/v0.7.4) released.
+
+**[Apr 5th 2023]:**   PyTorch3D [v0.7.3](https://github.com/facebookresearch/pytorch3d/releases/tag/v0.7.3) released.
+
 **[Dec 19th 2022]:**   PyTorch3D [v0.7.2](https://github.com/facebookresearch/pytorch3d/releases/tag/v0.7.2) released.
 
 **[Oct 23rd 2022]:**   PyTorch3D [v0.7.1](https://github.com/facebookresearch/pytorch3d/releases/tag/v0.7.1) released.

dev/linter.sh

@@ -10,7 +10,7 @@
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 DIR=$(dirname "${DIR}")
 
-if [[ -f "${DIR}/TARGETS" ]]
+if [[ -f "${DIR}/BUCK" ]]
 then
   pyfmt "${DIR}"
 else
@@ -36,5 +36,5 @@ then
 
   echo "Running pyre..."
   echo "To restart/kill pyre server, run 'pyre restart' or 'pyre kill' in fbcode/"
-  ( cd ~/fbsource/fbcode; pyre -l vision/fair/pytorch3d/ )
+  ( cd ~/fbsource/fbcode; arc pyre check //vision/fair/pytorch3d/... )
 fi

dev/run_tutorials.sh

@@ -23,7 +23,7 @@ conda init bash
 source ~/.bashrc
 conda create -y -n myenv python=3.8 matplotlib ipython ipywidgets nbconvert
 conda activate myenv
-conda install -y -c fvcore -c iopath -c conda-forge fvcore iopath
+conda install -y -c iopath iopath
 conda install -y -c pytorch pytorch=1.6.0 cudatoolkit=10.1 torchvision
 conda install -y -c pytorch3d-nightly pytorch3d
 pip install plotly scikit-image

docs/conf.py

@@ -19,7 +19,6 @@
 #
 import os
 import sys
-
 import unittest.mock as mock
 
 from recommonmark.parser import CommonMarkParser

docs/examples/pulsar_basic.py

@@ -10,6 +10,7 @@ This example demonstrates the most trivial, direct interface of the pulsar
 sphere renderer. It renders and saves an image with 10 random spheres.
 Output: basic.png.
 """
+
 import logging
 import math
 from os import path

docs/examples/pulsar_basic_unified.py

@@ -11,6 +11,7 @@ interface for sphere renderering. It renders and saves an image with
 10 random spheres.
 Output: basic-pt3d.png.
 """
+
 import logging
 from os import path
 

docs/examples/pulsar_cam.py

@@ -14,6 +14,7 @@ distorted. Gradient-based optimization is used to converge towards the
 original camera parameters.
 Output: cam.gif.
 """
+
 import logging
 import math
 from os import path

docs/examples/pulsar_cam_unified.py

@@ -14,6 +14,7 @@ distorted. Gradient-based optimization is used to converge towards the
 original camera parameters.
 Output: cam-pt3d.gif
 """
+
 import logging
 from os import path
 

docs/examples/pulsar_multiview.py

@@ -18,6 +18,7 @@ This example is not available yet through the 'unified' interface,
 because opacity support has not landed in PyTorch3D for general data
 structures yet.
 """
+
 import logging
 import math
 from os import path

docs/examples/pulsar_optimization.py

@@ -13,6 +13,7 @@ The scene is initialized with random spheres. Gradient-based
 optimization is used to converge towards a faithful
 scene representation.
 """
+
 import logging
 import math
 

docs/examples/pulsar_optimization_unified.py

@@ -13,6 +13,7 @@ The scene is initialized with random spheres. Gradient-based
 optimization is used to converge towards a faithful
 scene representation.
 """
+
 import logging
 import math
 

docs/requirements.txt

@@ -5,7 +5,6 @@ sphinx_rtd_theme
 sphinx_markdown_tables
 numpy
 iopath
-fvcore
 https://download.pytorch.org/whl/cpu/torchvision-0.15.2%2Bcpu-cp311-cp311-linux_x86_64.whl
 https://download.pytorch.org/whl/cpu/torch-2.0.1%2Bcpu-cp311-cp311-linux_x86_64.whl
 omegaconf

docs/tutorials/bundle_adjustment.ipynb

@@ -83,25 +83,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/camera_position_optimization_with_differentiable_rendering.ipynb

@@ -70,25 +70,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/dataloaders_ShapeNetCore_R2N2.ipynb

@@ -45,25 +45,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {
@@ -405,7 +411,7 @@
    "outputs": [],
    "source": [
     "random_model_images = shapenet_dataset.render(\n",
-    "    sample_nums=[3],\n",
+    "    sample_nums=[5],\n",
     "    device=device,\n",
     "    cameras=cameras,\n",
     "    raster_settings=raster_settings,\n",

docs/tutorials/deform_source_mesh_to_target_mesh.ipynb

@@ -84,25 +84,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/fit_simple_neural_radiance_field.ipynb

@@ -50,25 +50,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/fit_textured_mesh.ipynb

@@ -62,25 +62,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/fit_textured_volume.ipynb

@@ -41,25 +41,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/implicitron_config_system.ipynb

@@ -72,25 +72,31 @@
         "import os\n",
         "import sys\n",
         "import torch\n",
+        "import subprocess\n",
         "need_pytorch3d=False\n",
         "try:\n",
         "    import pytorch3d\n",
         "except ModuleNotFoundError:\n",
         "    need_pytorch3d=True\n",
         "if need_pytorch3d:\n",
-        "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+        "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-        "        # We try to install PyTorch3D via a released wheel.\n",
+        "    version_str=\"\".join([\n",
-        "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+        "        f\"py3{sys.version_info.minor}_cu\",\n",
-        "        version_str=\"\".join([\n",
+        "        torch.version.cuda.replace(\".\",\"\"),\n",
-        "            f\"py3{sys.version_info.minor}_cu\",\n",
+        "        f\"_pyt{pyt_version_str}\"\n",
-        "            torch.version.cuda.replace(\".\",\"\"),\n",
+        "    ])\n",
-        "            f\"_pyt{pyt_version_str}\"\n",
+        "    !pip install iopath\n",
-        "        ])\n",
+        "    if sys.platform.startswith(\"linux\"):\n",
-        "        !pip install fvcore iopath\n",
+        "        print(\"Trying to install wheel for PyTorch3D\")\n",
         "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-        "    else:\n",
+        "        pip_list = !pip freeze\n",
-        "        # We try to install PyTorch3D from source.\n",
+        "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-        "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+        "    if need_pytorch3d:\n",
+        "        print(f\"failed to find/install wheel for {version_str}\")\n",
+        "if need_pytorch3d:\n",
+        "    print(\"Installing PyTorch3D from source\")\n",
+        "    !pip install ninja\n",
+        "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
       ]
     },
     {

docs/tutorials/implicitron_volumes.ipynb

@@ -66,25 +66,31 @@
         "import os\n",
         "import sys\n",
         "import torch\n",
+        "import subprocess\n",
         "need_pytorch3d=False\n",
         "try:\n",
         "    import pytorch3d\n",
         "except ModuleNotFoundError:\n",
         "    need_pytorch3d=True\n",
         "if need_pytorch3d:\n",
-        "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+        "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-        "        # We try to install PyTorch3D via a released wheel.\n",
+        "    version_str=\"\".join([\n",
-        "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+        "        f\"py3{sys.version_info.minor}_cu\",\n",
-        "        version_str=\"\".join([\n",
+        "        torch.version.cuda.replace(\".\",\"\"),\n",
-        "            f\"py3{sys.version_info.minor}_cu\",\n",
+        "        f\"_pyt{pyt_version_str}\"\n",
-        "            torch.version.cuda.replace(\".\",\"\"),\n",
+        "    ])\n",
-        "            f\"_pyt{pyt_version_str}\"\n",
+        "    !pip install iopath\n",
-        "        ])\n",
+        "    if sys.platform.startswith(\"linux\"):\n",
-        "        !pip install fvcore iopath\n",
+        "        print(\"Trying to install wheel for PyTorch3D\")\n",
         "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-        "    else:\n",
+        "        pip_list = !pip freeze\n",
-        "        # We try to install PyTorch3D from source.\n",
+        "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-        "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+        "    if need_pytorch3d:\n",
+        "        print(f\"failed to find/install wheel for {version_str}\")\n",
+        "if need_pytorch3d:\n",
+        "    print(\"Installing PyTorch3D from source\")\n",
+        "    !pip install ninja\n",
+        "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
       ]
     },
     {

docs/tutorials/render_colored_points.ipynb

@@ -44,25 +44,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/render_densepose.ipynb

@@ -51,25 +51,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

docs/tutorials/render_textured_meshes.ipynb

@@ -67,25 +67,31 @@
     "import os\n",
     "import sys\n",
     "import torch\n",
+    "import subprocess\n",
     "need_pytorch3d=False\n",
     "try:\n",
     "    import pytorch3d\n",
     "except ModuleNotFoundError:\n",
     "    need_pytorch3d=True\n",
     "if need_pytorch3d:\n",
-    "    if torch.__version__.startswith(\"2.1.\") and sys.platform.startswith(\"linux\"):\n",
+    "    pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
-    "        # We try to install PyTorch3D via a released wheel.\n",
+    "    version_str=\"\".join([\n",
-    "        pyt_version_str=torch.__version__.split(\"+\")[0].replace(\".\", \"\")\n",
+    "        f\"py3{sys.version_info.minor}_cu\",\n",
-    "        version_str=\"\".join([\n",
+    "        torch.version.cuda.replace(\".\",\"\"),\n",
-    "            f\"py3{sys.version_info.minor}_cu\",\n",
+    "        f\"_pyt{pyt_version_str}\"\n",
-    "            torch.version.cuda.replace(\".\",\"\"),\n",
+    "    ])\n",
-    "            f\"_pyt{pyt_version_str}\"\n",
+    "    !pip install iopath\n",
-    "        ])\n",
+    "    if sys.platform.startswith(\"linux\"):\n",
-    "        !pip install fvcore iopath\n",
+    "        print(\"Trying to install wheel for PyTorch3D\")\n",
     "        !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html\n",
-    "    else:\n",
+    "        pip_list = !pip freeze\n",
-    "        # We try to install PyTorch3D from source.\n",
+    "        need_pytorch3d = not any(i.startswith(\"pytorch3d==\") for  i in pip_list)\n",
-    "        !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
+    "    if need_pytorch3d:\n",
+    "        print(f\"failed to find/install wheel for {version_str}\")\n",
+    "if need_pytorch3d:\n",
+    "    print(\"Installing PyTorch3D from source\")\n",
+    "    !pip install ninja\n",
+    "    !pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'"
    ]
   },
   {

packaging/build_conda.py

@@ -4,10 +4,11 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+import argparse
 import os.path
 import runpy
 import subprocess
-from typing import List
+from typing import List, Tuple
 
 # required env vars:
 # CU_VERSION: E.g. cu112
@@ -23,7 +24,7 @@ pytorch_major_minor = tuple(int(i) for i in PYTORCH_VERSION.split(".")[:2])
 source_root_dir = os.environ["PWD"]
 
 
-def version_constraint(version):
+def version_constraint(version) -> str:
     """
     Given version "11.3" returns " >=11.3,<11.4"
     """
@@ -32,7 +33,7 @@ def version_constraint(version):
     return f" >={version},<{upper}"
 
 
-def get_cuda_major_minor():
+def get_cuda_major_minor() -> Tuple[str, str]:
     if CU_VERSION == "cpu":
         raise ValueError("fn only for cuda builds")
     if len(CU_VERSION) != 5 or CU_VERSION[:2] != "cu":
@@ -42,11 +43,10 @@ def get_cuda_major_minor():
     return major, minor
 
 
-def setup_cuda():
+def setup_cuda(use_conda_cuda: bool) -> List[str]:
     if CU_VERSION == "cpu":
-        return
+        return []
     major, minor = get_cuda_major_minor()
-    os.environ["CUDA_HOME"] = f"/usr/local/cuda-{major}.{minor}/"
     os.environ["FORCE_CUDA"] = "1"
 
     basic_nvcc_flags = (
@@ -75,11 +75,26 @@ def setup_cuda():
 
     if os.environ.get("JUST_TESTRUN", "0") != "1":
         os.environ["NVCC_FLAGS"] = nvcc_flags
+    if use_conda_cuda:
+        os.environ["CONDA_CUDA_TOOLKIT_BUILD_CONSTRAINT1"] = "- cuda-toolkit"
+        os.environ["CONDA_CUDA_TOOLKIT_BUILD_CONSTRAINT2"] = (
+            f"- cuda-version={major}.{minor}"
+        )
+        return ["-c", f"nvidia/label/cuda-{major}.{minor}.0"]
+    else:
+        os.environ["CUDA_HOME"] = f"/usr/local/cuda-{major}.{minor}/"
+        return []
 
 
 def setup_conda_pytorch_constraint() -> List[str]:
     pytorch_constraint = f"- pytorch=={PYTORCH_VERSION}"
     os.environ["CONDA_PYTORCH_CONSTRAINT"] = pytorch_constraint
+    if pytorch_major_minor < (2, 2):
+        os.environ["CONDA_PYTORCH_MKL_CONSTRAINT"] = "- mkl!=2024.1.0"
+        os.environ["SETUPTOOLS_CONSTRAINT"] = "- setuptools<70"
+    else:
+        os.environ["CONDA_PYTORCH_MKL_CONSTRAINT"] = ""
+        os.environ["SETUPTOOLS_CONSTRAINT"] = "- setuptools"
     os.environ["CONDA_PYTORCH_BUILD_CONSTRAINT"] = pytorch_constraint
     os.environ["PYTORCH_VERSION_NODOT"] = PYTORCH_VERSION.replace(".", "")
 
@@ -89,7 +104,7 @@ def setup_conda_pytorch_constraint() -> List[str]:
         return ["-c", "pytorch", "-c", "nvidia"]
 
 
-def setup_conda_cudatoolkit_constraint():
+def setup_conda_cudatoolkit_constraint() -> None:
     if CU_VERSION == "cpu":
         os.environ["CONDA_CPUONLY_FEATURE"] = "- cpuonly"
         os.environ["CONDA_CUDATOOLKIT_CONSTRAINT"] = ""
@@ -110,14 +125,14 @@ def setup_conda_cudatoolkit_constraint():
     os.environ["CONDA_CUDATOOLKIT_CONSTRAINT"] = toolkit
 
 
-def do_build(start_args: List[str]):
+def do_build(start_args: List[str]) -> None:
     args = start_args.copy()
 
     test_flag = os.environ.get("TEST_FLAG")
     if test_flag is not None:
         args.append(test_flag)
 
-    args.extend(["-c", "bottler", "-c", "fvcore", "-c", "iopath", "-c", "conda-forge"])
+    args.extend(["-c", "bottler", "-c", "iopath", "-c", "conda-forge"])
     args.append("--no-anaconda-upload")
     args.extend(["--python", os.environ["PYTHON_VERSION"]])
     args.append("packaging/pytorch3d")
@@ -126,8 +141,16 @@ def do_build(start_args: List[str]):
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Build the conda package.")
+    parser.add_argument(
+        "--use-conda-cuda",
+        action="store_true",
+        help="get cuda from conda ignoring local cuda",
+    )
+    our_args = parser.parse_args()
+
     args = ["conda", "build"]
-    setup_cuda()
+    args += setup_cuda(use_conda_cuda=our_args.use_conda_cuda)
 
     init_path = source_root_dir + "/pytorch3d/__init__.py"
     build_version = runpy.run_path(init_path)["__version__"]

packaging/linux_wheels/README.md

@@ -26,6 +26,6 @@ version_str="".join([
     torch.version.cuda.replace(".",""),
     f"_pyt{pyt_version_str}"
 ])
-!pip install fvcore iopath
+!pip install iopath
 !pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html
 ```

packaging/linux_wheels/inside.sh

@@ -144,7 +144,7 @@ do
             conda activate "$tag"
             # shellcheck disable=SC2086
             conda install -y -c pytorch $extra_channel "pytorch=$pytorch_version" "$cudatools=$CUDA_TAG"
-            pip install fvcore iopath
+            pip install iopath
             echo "python version" "$python_version" "pytorch version" "$pytorch_version" "cuda version" "$cu_version" "tag" "$tag"
 
             rm -rf dist

packaging/pytorch3d/meta.yaml

@@ -8,12 +8,16 @@ source:
 requirements:
   build:
     - {{ compiler('c') }} # [win]
+    {{ environ.get('CONDA_CUDA_TOOLKIT_BUILD_CONSTRAINT1', '') }}
+    {{ environ.get('CONDA_CUDA_TOOLKIT_BUILD_CONSTRAINT2', '') }}
     {{ environ.get('CONDA_CUB_CONSTRAINT') }}
 
   host:
     - python
-    - setuptools
+    - mkl =2023  # [x86_64]
+    {{ environ.get('SETUPTOOLS_CONSTRAINT') }}
     {{ environ.get('CONDA_PYTORCH_BUILD_CONSTRAINT') }}
+    {{ environ.get('CONDA_PYTORCH_MKL_CONSTRAINT') }}
     {{ environ.get('CONDA_CUDATOOLKIT_CONSTRAINT') }}
     {{ environ.get('CONDA_CPUONLY_FEATURE') }}
 
@@ -21,7 +25,7 @@ requirements:
     - python
     - numpy >=1.11
     - torchvision >=0.5
-    - fvcore
+    - mkl =2023  # [x86_64]
     - iopath
     {{ environ.get('CONDA_PYTORCH_CONSTRAINT') }}
     {{ environ.get('CONDA_CUDATOOLKIT_CONSTRAINT') }}
@@ -47,8 +51,11 @@ test:
     - imageio
     - hydra-core
     - accelerate
+    - matplotlib
+    - tabulate
+    - pandas
+    - sqlalchemy
   commands:
-    #pytest .
     python -m unittest discover -v -s tests -t .
 
 

projects/implicitron_trainer/__init__.py

@@ -3,3 +3,5 @@
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
+
+# pyre-unsafe

projects/implicitron_trainer/experiment.py

@@ -5,7 +5,9 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
-""""
+# pyre-unsafe
+
+""" "
 This file is the entry point for launching experiments with Implicitron.
 
 Launch Training
@@ -42,25 +44,22 @@ The outputs of the experiment are saved and logged in multiple ways:
         config file.
 
 """
+
 import logging
 import os
 import warnings
-
 from dataclasses import field
 
 import hydra
-
 import torch
 from accelerate import Accelerator
 from omegaconf import DictConfig, OmegaConf
 from packaging import version
-
 from pytorch3d.implicitron.dataset.data_source import (
     DataSourceBase,
     ImplicitronDataSource,
 )
 from pytorch3d.implicitron.models.base_model import ImplicitronModelBase
-
 from pytorch3d.implicitron.models.renderer.multipass_ea import (
     MultiPassEmissionAbsorptionRenderer,
 )
@@ -97,7 +96,7 @@ except ModuleNotFoundError:
 no_accelerate = os.environ.get("PYTORCH3D_NO_ACCELERATE") is not None
 
 
-class Experiment(Configurable):  # pyre-ignore: 13
+class Experiment(Configurable):
     """
     This class is at the top level of Implicitron's config hierarchy. Its
     members are high-level components necessary for training an implicit rende-
@@ -118,12 +117,16 @@ class Experiment(Configurable):  # pyre-ignore: 13
             will be saved here.
     """
 
+    # pyre-fixme[13]: Attribute `data_source` is never initialized.
     data_source: DataSourceBase
     data_source_class_type: str = "ImplicitronDataSource"
+    # pyre-fixme[13]: Attribute `model_factory` is never initialized.
     model_factory: ModelFactoryBase
     model_factory_class_type: str = "ImplicitronModelFactory"
+    # pyre-fixme[13]: Attribute `optimizer_factory` is never initialized.
     optimizer_factory: OptimizerFactoryBase
     optimizer_factory_class_type: str = "ImplicitronOptimizerFactory"
+    # pyre-fixme[13]: Attribute `training_loop` is never initialized.
     training_loop: TrainingLoopBase
     training_loop_class_type: str = "ImplicitronTrainingLoop"
 

projects/implicitron_trainer/impl/__init__.py

@@ -3,3 +3,5 @@
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
+
+# pyre-unsafe

projects/implicitron_trainer/impl/model_factory.py

@@ -4,12 +4,13 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import logging
 import os
 from typing import Optional
 
 import torch.optim
-
 from accelerate import Accelerator
 from pytorch3d.implicitron.models.base_model import ImplicitronModelBase
 from pytorch3d.implicitron.tools import model_io
@@ -24,7 +25,6 @@ logger = logging.getLogger(__name__)
 
 
 class ModelFactoryBase(ReplaceableBase):
-
     resume: bool = True  # resume from the last checkpoint
 
     def __call__(self, **kwargs) -> ImplicitronModelBase:
@@ -43,7 +43,7 @@ class ModelFactoryBase(ReplaceableBase):
 
 
 @registry.register
-class ImplicitronModelFactory(ModelFactoryBase):  # pyre-ignore [13]
+class ImplicitronModelFactory(ModelFactoryBase):
     """
     A factory class that initializes an implicit rendering model.
 
@@ -59,6 +59,7 @@ class ImplicitronModelFactory(ModelFactoryBase):  # pyre-ignore [13]
 
     """
 
+    # pyre-fixme[13]: Attribute `model` is never initialized.
     model: ImplicitronModelBase
     model_class_type: str = "GenericModel"
     resume: bool = True
@@ -113,7 +114,9 @@ class ImplicitronModelFactory(ModelFactoryBase):  # pyre-ignore [13]
                         "cuda:%d" % 0: "cuda:%d" % accelerator.local_process_index
                     }
                 model_state_dict = torch.load(
-                    model_io.get_model_path(model_path), map_location=map_location
+                    model_io.get_model_path(model_path),
+                    map_location=map_location,
+                    weights_only=True,
                 )
 
                 try:

projects/implicitron_trainer/impl/optimizer_factory.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import inspect
 import logging
 import os
@@ -12,9 +14,7 @@ from dataclasses import field
 from typing import Any, Dict, List, Optional, Tuple
 
 import torch.optim
-
 from accelerate import Accelerator
-
 from pytorch3d.implicitron.models.base_model import ImplicitronModelBase
 from pytorch3d.implicitron.tools import model_io
 from pytorch3d.implicitron.tools.config import (
@@ -121,7 +121,7 @@ class ImplicitronOptimizerFactory(OptimizerFactoryBase):
         """
         # Get the parameters to optimize
         if hasattr(model, "_get_param_groups"):  # use the model function
-            # pyre-ignore[29]
+            # pyre-fixme[29]: `Union[Tensor, Module]` is not a function.
             p_groups = model._get_param_groups(self.lr, wd=self.weight_decay)
         else:
             p_groups = [
@@ -240,7 +240,7 @@ class ImplicitronOptimizerFactory(OptimizerFactoryBase):
                     map_location = {
                         "cuda:%d" % 0: "cuda:%d" % accelerator.local_process_index
                     }
-                optimizer_state = torch.load(opt_path, map_location)
+                optimizer_state = torch.load(opt_path, map_location, weights_only=True)
             else:
                 raise FileNotFoundError(f"Optimizer state {opt_path} does not exist.")
         return optimizer_state

projects/implicitron_trainer/impl/training_loop.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import logging
 import os
 import time
@@ -28,13 +30,13 @@ from .utils import seed_all_random_engines
 logger = logging.getLogger(__name__)
 
 
-# pyre-fixme[13]: Attribute `evaluator` is never initialized.
 class TrainingLoopBase(ReplaceableBase):
     """
     Members:
         evaluator: An EvaluatorBase instance, used to evaluate training results.
     """
 
+    # pyre-fixme[13]: Attribute `evaluator` is never initialized.
     evaluator: Optional[EvaluatorBase]
     evaluator_class_type: Optional[str] = "ImplicitronEvaluator"
 
@@ -110,6 +112,8 @@ class ImplicitronTrainingLoop(TrainingLoopBase):
     def __post_init__(self):
         run_auto_creation(self)
 
+    # pyre-fixme[14]: `run` overrides method defined in `TrainingLoopBase`
+    #  inconsistently.
     def run(
         self,
         *,
@@ -157,7 +161,6 @@ class ImplicitronTrainingLoop(TrainingLoopBase):
         for epoch in range(start_epoch, self.max_epochs):
             # automatic new_epoch and plotting of stats at every epoch start
             with stats:
-
                 # Make sure to re-seed random generators to ensure reproducibility
                 # even after restart.
                 seed_all_random_engines(seed + epoch)
@@ -391,7 +394,7 @@ class ImplicitronTrainingLoop(TrainingLoopBase):
             ):
                 prefix = f"e{stats.epoch}_it{stats.it[trainmode]}"
                 if hasattr(model, "visualize"):
-                    # pyre-ignore [29]
+                    # pyre-fixme[29]: `Union[Tensor, Module]` is not a function.
                     model.visualize(
                         viz,
                         visdom_env_imgs,

projects/implicitron_trainer/impl/utils.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 
 import random
 

projects/implicitron_trainer/tests/__init__.py

@@ -3,3 +3,5 @@
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
+
+# pyre-unsafe

projects/implicitron_trainer/tests/test_experiment.py

@@ -4,13 +4,14 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import os
 import tempfile
 import unittest
 from pathlib import Path
 
 import torch
-
 from hydra import compose, initialize_config_dir
 from omegaconf import OmegaConf
 from projects.implicitron_trainer.impl.optimizer_factory import (
@@ -51,12 +52,8 @@ class TestExperiment(unittest.TestCase):
         cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_class_type = (
             "JsonIndexDatasetMapProvider"
         )
-        dataset_args = (
+        dataset_args = cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
-            cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
+        dataloader_args = cfg.data_source_ImplicitronDataSource_args.data_loader_map_provider_SequenceDataLoaderMapProvider_args
-        )
-        dataloader_args = (
-            cfg.data_source_ImplicitronDataSource_args.data_loader_map_provider_SequenceDataLoaderMapProvider_args
-        )
         dataset_args.category = "skateboard"
         dataset_args.test_restrict_sequence_id = 0
         dataset_args.dataset_root = "manifold://co3d/tree/extracted"
@@ -92,12 +89,8 @@ class TestExperiment(unittest.TestCase):
         cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_class_type = (
             "JsonIndexDatasetMapProvider"
         )
-        dataset_args = (
+        dataset_args = cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
-            cfg.data_source_ImplicitronDataSource_args.dataset_map_provider_JsonIndexDatasetMapProvider_args
+        dataloader_args = cfg.data_source_ImplicitronDataSource_args.data_loader_map_provider_SequenceDataLoaderMapProvider_args
-        )
-        dataloader_args = (
-            cfg.data_source_ImplicitronDataSource_args.data_loader_map_provider_SequenceDataLoaderMapProvider_args
-        )
         dataset_args.category = "skateboard"
         dataset_args.test_restrict_sequence_id = 0
         dataset_args.dataset_root = "manifold://co3d/tree/extracted"
@@ -109,9 +102,7 @@ class TestExperiment(unittest.TestCase):
         cfg.training_loop_ImplicitronTrainingLoop_args.max_epochs = 2
         cfg.training_loop_ImplicitronTrainingLoop_args.store_checkpoints = False
         cfg.optimizer_factory_ImplicitronOptimizerFactory_args.lr_policy = "Exponential"
-        cfg.optimizer_factory_ImplicitronOptimizerFactory_args.exponential_lr_step_size = (
+        cfg.optimizer_factory_ImplicitronOptimizerFactory_args.exponential_lr_step_size = 2
-            2
-        )
 
         if DEBUG:
             experiment.dump_cfg(cfg)

projects/implicitron_trainer/tests/test_optimizer_factory.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import logging
 import os
 import unittest
@@ -79,8 +81,9 @@ class TestOptimizerFactory(unittest.TestCase):
 
     def test_param_overrides_self_param_group_assignment(self):
         pa, pb, pc = [torch.nn.Parameter(data=torch.tensor(i * 1.0)) for i in range(3)]
-        na, nb = Node(params=[pa]), Node(
+        na, nb = (
-            params=[pb], param_groups={"self": "pb_self", "p1": "pb_param"}
+            Node(params=[pa]),
+            Node(params=[pb], param_groups={"self": "pb_self", "p1": "pb_param"}),
         )
         root = Node(children=[na, nb], params=[pc], param_groups={"m1": "pb_member"})
         param_groups = self._get_param_groups(root)

projects/implicitron_trainer/tests/test_visualize.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import os
 import unittest
 

projects/implicitron_trainer/tests/utils.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import contextlib
 import logging
 import os

projects/implicitron_trainer/visualize_reconstruction.py

@@ -5,6 +5,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 """
 Script to visualize a previously trained model. Example call:
 

projects/nerf/nerf/dataset.py

@@ -84,9 +84,9 @@ def get_nerf_datasets(
 
     if autodownload and any(not os.path.isfile(p) for p in (cameras_path, image_path)):
         # Automatically download the data files if missing.
-        download_data((dataset_name,), data_root=data_root)
+        download_data([dataset_name], data_root=data_root)
 
-    train_data = torch.load(cameras_path)
+    train_data = torch.load(cameras_path, weights_only=True)
     n_cameras = train_data["cameras"]["R"].shape[0]
 
     _image_max_image_pixels = Image.MAX_IMAGE_PIXELS

projects/nerf/nerf/nerf_renderer.py

@@ -343,12 +343,14 @@ class RadianceFieldRenderer(torch.nn.Module):
             # For a full render pass concatenate the output chunks,
             # and reshape to image size.
             out = {
-                k: torch.cat(
+                k: (
-                    [ch_o[k] for ch_o in chunk_outputs],
+                    torch.cat(
-                    dim=1,
+                        [ch_o[k] for ch_o in chunk_outputs],
-                ).view(-1, *self._image_size, 3)
+                        dim=1,
-                if chunk_outputs[0][k] is not None
+                    ).view(-1, *self._image_size, 3)
-                else None
+                    if chunk_outputs[0][k] is not None
+                    else None
+                )
                 for k in ("rgb_fine", "rgb_coarse", "rgb_gt")
             }
         else:

projects/nerf/nerf/stats.py

@@ -194,7 +194,6 @@ class Stats:
         it = self.it[stat_set]
 
         for stat in self.log_vars:
-
             if stat not in self.stats[stat_set]:
                 self.stats[stat_set][stat] = AverageMeter()
 

projects/nerf/test_nerf.py

@@ -24,7 +24,6 @@ CONFIG_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), "configs"
 
 @hydra.main(config_path=CONFIG_DIR, config_name="lego")
 def main(cfg: DictConfig):
-
     # Device on which to run.
     if torch.cuda.is_available():
         device = "cuda"
@@ -63,7 +62,7 @@ def main(cfg: DictConfig):
         raise ValueError(f"Model checkpoint {checkpoint_path} does not exist!")
 
     print(f"Loading checkpoint {checkpoint_path}.")
-    loaded_data = torch.load(checkpoint_path)
+    loaded_data = torch.load(checkpoint_path, weights_only=True)
     # Do not load the cached xy grid.
     # - this allows setting an arbitrary evaluation image size.
     state_dict = {

projects/nerf/tests/test_raysampler.py

@@ -42,7 +42,6 @@ class TestRaysampler(unittest.TestCase):
         cameras, rays = [], []
 
         for _ in range(batch_size):
-
             R = random_rotations(1)
             T = torch.randn(1, 3)
             focal_length = torch.rand(1, 2) + 0.5

projects/nerf/train_nerf.py

@@ -25,7 +25,6 @@ CONFIG_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), "configs"
 
 @hydra.main(config_path=CONFIG_DIR, config_name="lego")
 def main(cfg: DictConfig):
-
     # Set the relevant seeds for reproducibility.
     np.random.seed(cfg.seed)
     torch.manual_seed(cfg.seed)
@@ -77,7 +76,7 @@ def main(cfg: DictConfig):
         # Resume training if requested.
         if cfg.resume and os.path.isfile(checkpoint_path):
             print(f"Resuming from checkpoint {checkpoint_path}.")
-            loaded_data = torch.load(checkpoint_path)
+            loaded_data = torch.load(checkpoint_path, weights_only=True)
             model.load_state_dict(loaded_data["model"])
             stats = pickle.loads(loaded_data["stats"])
             print(f"   => resuming from epoch {stats.epoch}.")
@@ -219,7 +218,6 @@ def main(cfg: DictConfig):
 
         # Validation
         if epoch % cfg.validation_epoch_interval == 0 and epoch > 0:
-
             # Sample a validation camera/image.
             val_batch = next(val_dataloader.__iter__())
             val_image, val_camera, camera_idx = val_batch[0].values()

pytorch3d/__init__.py

@@ -4,4 +4,6 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
-__version__ = "0.7.5"
+# pyre-unsafe
+
+__version__ = "0.7.9"

pytorch3d/common/__init__.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 from .datatypes import Device, get_device, make_device
 
 

pytorch3d/common/compat.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 from typing import Sequence, Tuple, Union
 
 import torch
@@ -15,7 +17,7 @@ Some functions which depend on PyTorch or Python versions.
 
 
 def meshgrid_ij(
-    *A: Union[torch.Tensor, Sequence[torch.Tensor]]
+    *A: Union[torch.Tensor, Sequence[torch.Tensor]],
 ) -> Tuple[torch.Tensor, ...]:  # pragma: no cover
     """
     Like torch.meshgrid was before PyTorch 1.10.0, i.e. with indexing set to ij

pytorch3d/common/datatypes.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 from typing import Optional, Union
 
 import torch

pytorch3d/common/linear_with_repeat.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import math
 from typing import Tuple
 

pytorch3d/common/workaround/__init__.py

@@ -4,5 +4,7 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 from .symeig3x3 import symeig3x3
 from .utils import _safe_det_3x3

pytorch3d/common/workaround/symeig3x3.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 import math
 from typing import Optional, Tuple
 

pytorch3d/common/workaround/utils.py

@@ -4,6 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+# pyre-unsafe
+
 
 import torch
 

pytorch3d/csrc/ball_query/ball_query.cu

@@ -32,7 +32,9 @@ __global__ void BallQueryKernel(
     at::PackedTensorAccessor64<int64_t, 3, at::RestrictPtrTraits> idxs,
     at::PackedTensorAccessor64<scalar_t, 3, at::RestrictPtrTraits> dists,
     const int64_t K,
-    const float radius2) {
+    const float radius,
+    const float radius2,
+    const bool skip_points_outside_cube) {
   const int64_t N = p1.size(0);
   const int64_t chunks_per_cloud = (1 + (p1.size(1) - 1) / blockDim.x);
   const int64_t chunks_to_do = N * chunks_per_cloud;
@@ -51,7 +53,19 @@ __global__ void BallQueryKernel(
     // Iterate over points in p2 until desired count is reached or
     // all points have been considered
     for (int64_t j = 0, count = 0; j < lengths2[n] && count < K; ++j) {
-      // Calculate the distance between the points
+      if (skip_points_outside_cube) {
+        bool is_within_radius = true;
+        // Filter when any one coordinate is already outside the radius
+        for (int d = 0; is_within_radius && d < D; ++d) {
+          scalar_t abs_diff = fabs(p1[n][i][d] - p2[n][j][d]);
+          is_within_radius = (abs_diff <= radius);
+        }
+        if (!is_within_radius) {
+          continue;
+        }
+      }
+
+      // Else, calculate the distance between the points and compare
       scalar_t dist2 = 0.0;
       for (int d = 0; d < D; ++d) {
         scalar_t diff = p1[n][i][d] - p2[n][j][d];
@@ -77,7 +91,8 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCuda(
     const at::Tensor& lengths1, // (N,)
     const at::Tensor& lengths2, // (N,)
     int K,
-    float radius) {
+    float radius,
+    bool skip_points_outside_cube) {
   // Check inputs are on the same device
   at::TensorArg p1_t{p1, "p1", 1}, p2_t{p2, "p2", 2},
       lengths1_t{lengths1, "lengths1", 3}, lengths2_t{lengths2, "lengths2", 4};
@@ -120,7 +135,9 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCuda(
             idxs.packed_accessor64<int64_t, 3, at::RestrictPtrTraits>(),
             dists.packed_accessor64<float, 3, at::RestrictPtrTraits>(),
             K_64,
-            radius2);
+            radius,
+            radius2,
+            skip_points_outside_cube);
       }));
 
   AT_CUDA_CHECK(cudaGetLastError());

pytorch3d/csrc/ball_query/ball_query.h

@@ -25,6 +25,9 @@
 //      within the radius
 //    radius: the radius around each point within which the neighbors need to be
 //      located
+//    skip_points_outside_cube: If true, reduce multiplications of float values
+//      by not explicitly calculating distances to points that fall outside the
+//      D-cube with side length (2*radius) centered at each point in p1.
 //
 // Returns:
 //    p1_neighbor_idx: LongTensor of shape (N, P1, K), where
@@ -46,7 +49,8 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCpu(
     const at::Tensor& lengths1,
     const at::Tensor& lengths2,
     const int K,
-    const float radius);
+    const float radius,
+    const bool skip_points_outside_cube);
 
 // CUDA implementation
 std::tuple<at::Tensor, at::Tensor> BallQueryCuda(
@@ -55,7 +59,8 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCuda(
     const at::Tensor& lengths1,
     const at::Tensor& lengths2,
     const int K,
-    const float radius);
+    const float radius,
+    const bool skip_points_outside_cube);
 
 // Implementation which is exposed
 // Note: the backward pass reuses the KNearestNeighborBackward kernel
@@ -65,7 +70,8 @@ inline std::tuple<at::Tensor, at::Tensor> BallQuery(
     const at::Tensor& lengths1,
     const at::Tensor& lengths2,
     int K,
-    float radius) {
+    float radius,
+    bool skip_points_outside_cube) {
   if (p1.is_cuda() || p2.is_cuda()) {
 #ifdef WITH_CUDA
     CHECK_CUDA(p1);
@@ -76,16 +82,20 @@ inline std::tuple<at::Tensor, at::Tensor> BallQuery(
         lengths1.contiguous(),
         lengths2.contiguous(),
         K,
-        radius);
+        radius,
+        skip_points_outside_cube);
 #else
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(p1);
+  CHECK_CPU(p2);
   return BallQueryCpu(
       p1.contiguous(),
       p2.contiguous(),
       lengths1.contiguous(),
       lengths2.contiguous(),
       K,
-      radius);
+      radius,
+      skip_points_outside_cube);
 }

pytorch3d/csrc/ball_query/ball_query_cpu.cpp

@@ -6,8 +6,8 @@
  * LICENSE file in the root directory of this source tree.
  */
 
+#include <math.h>
 #include <torch/extension.h>
-#include <queue>
 #include <tuple>
 
 std::tuple<at::Tensor, at::Tensor> BallQueryCpu(
@@ -16,7 +16,8 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCpu(
     const at::Tensor& lengths1,
     const at::Tensor& lengths2,
     int K,
-    float radius) {
+    float radius,
+    bool skip_points_outside_cube) {
   const int N = p1.size(0);
   const int P1 = p1.size(1);
   const int D = p1.size(2);
@@ -38,6 +39,16 @@ std::tuple<at::Tensor, at::Tensor> BallQueryCpu(
     const int64_t length2 = lengths2_a[n];
     for (int64_t i = 0; i < length1; ++i) {
       for (int64_t j = 0, count = 0; j < length2 && count < K; ++j) {
+        if (skip_points_outside_cube) {
+          bool is_within_radius = true;
+          for (int d = 0; is_within_radius && d < D; ++d) {
+            float abs_diff = fabs(p1_a[n][i][d] - p2_a[n][j][d]);
+            is_within_radius = (abs_diff <= radius);
+          }
+          if (!is_within_radius) {
+            continue;
+          }
+        }
         float dist2 = 0;
         for (int d = 0; d < D; ++d) {
           float diff = p1_a[n][i][d] - p2_a[n][j][d];

pytorch3d/csrc/blending/sigmoid_alpha_blend.h

@@ -98,6 +98,11 @@ at::Tensor SigmoidAlphaBlendBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(distances);
+  CHECK_CPU(pix_to_face);
+  CHECK_CPU(alphas);
+  CHECK_CPU(grad_alphas);
+
   return SigmoidAlphaBlendBackwardCpu(
       grad_alphas, alphas, distances, pix_to_face, sigma);
 }

pytorch3d/csrc/compositing/alpha_composite.cu

@@ -28,17 +28,16 @@ __global__ void alphaCompositeCudaForwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = result.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * H * W;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Iterate over each feature in each pixel
   for (int pid = tid; pid < num_pixels; pid += num_threads) {
@@ -79,17 +78,16 @@ __global__ void alphaCompositeCudaBackwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = points_idx.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * H * W;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Parallelize over each feature in each pixel in images of size H * W,
   // for each image in the batch of size batch_size

pytorch3d/csrc/compositing/alpha_composite.h

@@ -74,6 +74,9 @@ torch::Tensor alphaCompositeForward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
     return alphaCompositeCpuForward(features, alphas, points_idx);
   }
 }
@@ -101,6 +104,11 @@ std::tuple<torch::Tensor, torch::Tensor> alphaCompositeBackward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(grad_outputs);
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
+
     return alphaCompositeCpuBackward(
         grad_outputs, features, alphas, points_idx);
   }

pytorch3d/csrc/compositing/norm_weighted_sum.cu

@@ -28,17 +28,16 @@ __global__ void weightedSumNormCudaForwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = result.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * H * W;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Parallelize over each feature in each pixel in images of size H * W,
   // for each image in the batch of size batch_size
@@ -92,17 +91,16 @@ __global__ void weightedSumNormCudaBackwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = points_idx.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * W * H;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Parallelize over each feature in each pixel in images of size H * W,
   // for each image in the batch of size batch_size

pytorch3d/csrc/compositing/norm_weighted_sum.h

@@ -73,6 +73,10 @@ torch::Tensor weightedSumNormForward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
+
     return weightedSumNormCpuForward(features, alphas, points_idx);
   }
 }
@@ -100,6 +104,11 @@ std::tuple<torch::Tensor, torch::Tensor> weightedSumNormBackward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(grad_outputs);
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
+
     return weightedSumNormCpuBackward(
         grad_outputs, features, alphas, points_idx);
   }

pytorch3d/csrc/compositing/weighted_sum.cu

@@ -26,17 +26,16 @@ __global__ void weightedSumCudaForwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = result.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * H * W;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Parallelize over each feature in each pixel in images of size H * W,
   // for each image in the batch of size batch_size
@@ -74,17 +73,16 @@ __global__ void weightedSumCudaBackwardKernel(
     const at::PackedTensorAccessor64<float, 4, at::RestrictPtrTraits> alphas,
     const at::PackedTensorAccessor64<int64_t, 4, at::RestrictPtrTraits> points_idx) {
   // clang-format on
-  const int64_t batch_size = points_idx.size(0);
   const int64_t C = features.size(0);
   const int64_t H = points_idx.size(2);
   const int64_t W = points_idx.size(3);
 
   // Get the batch and index
-  const int batch = blockIdx.x;
+  const auto batch = blockIdx.x;
 
   const int num_pixels = C * H * W;
-  const int num_threads = gridDim.y * blockDim.x;
+  const auto num_threads = gridDim.y * blockDim.x;
-  const int tid = blockIdx.y * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.y * blockDim.x + threadIdx.x;
 
   // Iterate over each pixel to compute the contribution to the
   // gradient for the features and weights

pytorch3d/csrc/compositing/weighted_sum.h

@@ -72,6 +72,9 @@ torch::Tensor weightedSumForward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
     return weightedSumCpuForward(features, alphas, points_idx);
   }
 }
@@ -98,6 +101,11 @@ std::tuple<torch::Tensor, torch::Tensor> weightedSumBackward(
     AT_ERROR("Not compiled with GPU support");
 #endif
   } else {
+    CHECK_CPU(grad_outputs);
+    CHECK_CPU(features);
+    CHECK_CPU(alphas);
+    CHECK_CPU(points_idx);
+
     return weightedSumCpuBackward(grad_outputs, features, alphas, points_idx);
   }
 }

pytorch3d/csrc/ext.cpp

@@ -8,7 +8,6 @@
 
 // clang-format off
 #include "./pulsar/global.h" // Include before <torch/extension.h>.
-#include <torch/extension.h>
 // clang-format on
 #include "./pulsar/pytorch/renderer.h"
 #include "./pulsar/pytorch/tensor_util.h"
@@ -99,21 +98,23 @@ PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
   m.def("marching_cubes", &MarchingCubes);
 
   // Pulsar.
+  // Pulsar not enabled on AMD.
 #ifdef PULSAR_LOGGING_ENABLED
   c10::ShowLogInfoToStderr();
 #endif
   py::class_<
       pulsar::pytorch::Renderer,
       std::shared_ptr<pulsar::pytorch::Renderer>>(m, "PulsarRenderer")
-      .def(py::init<
+      .def(
-           const uint&,
+          py::init<
-           const uint&,
+              const uint&,
-           const uint&,
+              const uint&,
-           const bool&,
+              const uint&,
-           const bool&,
+              const bool&,
-           const float&,
+              const bool&,
-           const uint&,
+              const float&,
-           const uint&>())
+              const uint&,
+              const uint&>())
       .def(
           "__eq__",
           [](const pulsar::pytorch::Renderer& a,
@@ -148,10 +149,10 @@ PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
           py::arg("gamma"),
           py::arg("max_depth"),
           py::arg("min_depth") /* = 0.f*/,
-          py::arg(
+          py::arg("bg_col") /* = std::nullopt not exposed properly in
-              "bg_col") /* = at::nullopt not exposed properly in pytorch 1.1. */
+                               pytorch 1.1. */
           ,
-          py::arg("opacity") /* = at::nullopt ... */,
+          py::arg("opacity") /* = std::nullopt ... */,
           py::arg("percent_allowed_difference") = 0.01f,
           py::arg("max_n_hits") = MAX_UINT,
           py::arg("mode") = 0)

pytorch3d/csrc/face_areas_normals/face_areas_normals.h

@@ -60,6 +60,8 @@ std::tuple<at::Tensor, at::Tensor> FaceAreasNormalsForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(verts);
+  CHECK_CPU(faces);
   return FaceAreasNormalsForwardCpu(verts, faces);
 }
 
@@ -80,5 +82,9 @@ at::Tensor FaceAreasNormalsBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(grad_areas);
+  CHECK_CPU(grad_normals);
+  CHECK_CPU(verts);
+  CHECK_CPU(faces);
   return FaceAreasNormalsBackwardCpu(grad_areas, grad_normals, verts, faces);
 }

pytorch3d/csrc/gather_scatter/gather_scatter.cu

@@ -20,14 +20,14 @@ __global__ void GatherScatterCudaKernel(
     const size_t V,
     const size_t D,
     const size_t E) {
-  const int tid = threadIdx.x;
+  const auto tid = threadIdx.x;
 
   // Reverse the vertex order if backward.
   const int v0_idx = backward ? 1 : 0;
   const int v1_idx = backward ? 0 : 1;
 
   // Edges are split evenly across the blocks.
-  for (int e = blockIdx.x; e < E; e += gridDim.x) {
+  for (auto e = blockIdx.x; e < E; e += gridDim.x) {
     // Get indices of vertices which form the edge.
     const int64_t v0 = edges[2 * e + v0_idx];
     const int64_t v1 = edges[2 * e + v1_idx];
@@ -35,7 +35,7 @@ __global__ void GatherScatterCudaKernel(
     // Split vertex features evenly across threads.
     // This implementation will be quite wasteful when D<128 since there will be
     // a lot of threads doing nothing.
-    for (int d = tid; d < D; d += blockDim.x) {
+    for (auto d = tid; d < D; d += blockDim.x) {
       const float val = input[v1 * D + d];
       float* address = output + v0 * D + d;
       atomicAdd(address, val);

pytorch3d/csrc/gather_scatter/gather_scatter.h

@@ -53,5 +53,7 @@ at::Tensor GatherScatter(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(input);
+  CHECK_CPU(edges);
   return GatherScatterCpu(input, edges, directed, backward);
 }

pytorch3d/csrc/interp_face_attrs/interp_face_attrs.cu

@@ -20,8 +20,8 @@ __global__ void InterpFaceAttrsForwardKernel(
     const size_t P,
     const size_t F,
     const size_t D) {
-  const int tid = threadIdx.x + blockIdx.x * blockDim.x;
+  const auto tid = threadIdx.x + blockIdx.x * blockDim.x;
-  const int num_threads = blockDim.x * gridDim.x;
+  const auto num_threads = blockDim.x * gridDim.x;
   for (int pd = tid; pd < P * D; pd += num_threads) {
     const int p = pd / D;
     const int d = pd % D;
@@ -93,8 +93,8 @@ __global__ void InterpFaceAttrsBackwardKernel(
     const size_t P,
     const size_t F,
     const size_t D) {
-  const int tid = threadIdx.x + blockIdx.x * blockDim.x;
+  const auto tid = threadIdx.x + blockIdx.x * blockDim.x;
-  const int num_threads = blockDim.x * gridDim.x;
+  const auto num_threads = blockDim.x * gridDim.x;
   for (int pd = tid; pd < P * D; pd += num_threads) {
     const int p = pd / D;
     const int d = pd % D;

pytorch3d/csrc/interp_face_attrs/interp_face_attrs.h

@@ -57,6 +57,8 @@ at::Tensor InterpFaceAttrsForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(face_attrs);
+  CHECK_CPU(barycentric_coords);
   return InterpFaceAttrsForwardCpu(pix_to_face, barycentric_coords, face_attrs);
 }
 
@@ -106,6 +108,9 @@ std::tuple<at::Tensor, at::Tensor> InterpFaceAttrsBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(face_attrs);
+  CHECK_CPU(barycentric_coords);
+  CHECK_CPU(grad_pix_attrs);
   return InterpFaceAttrsBackwardCpu(
       pix_to_face, barycentric_coords, face_attrs, grad_pix_attrs);
 }

pytorch3d/csrc/iou_box3d/iou_box3d.h

@@ -44,5 +44,7 @@ inline std::tuple<at::Tensor, at::Tensor> IoUBox3D(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(boxes1);
+  CHECK_CPU(boxes2);
   return IoUBox3DCpu(boxes1.contiguous(), boxes2.contiguous());
 }

pytorch3d/csrc/iou_box3d/iou_box3d_cpu.cpp

@@ -7,10 +7,7 @@
  */
 
 #include <torch/extension.h>
-#include <torch/torch.h>
 #include <list>
-#include <numeric>
-#include <queue>
 #include <tuple>
 #include "iou_box3d/iou_utils.h"
 

pytorch3d/csrc/iou_box3d/iou_utils.cuh

@@ -461,10 +461,8 @@ __device__ inline std::tuple<float3, float3> ArgMaxVerts(
 __device__ inline bool IsCoplanarTriTri(
     const FaceVerts& tri1,
     const FaceVerts& tri2) {
-  const float3 tri1_ctr = FaceCenter({tri1.v0, tri1.v1, tri1.v2});
   const float3 tri1_n = FaceNormal({tri1.v0, tri1.v1, tri1.v2});
 
-  const float3 tri2_ctr = FaceCenter({tri2.v0, tri2.v1, tri2.v2});
   const float3 tri2_n = FaceNormal({tri2.v0, tri2.v1, tri2.v2});
 
   // Check if parallel
@@ -500,7 +498,6 @@ __device__ inline bool IsCoplanarTriPlane(
     const FaceVerts& tri,
     const FaceVerts& plane,
     const float3& normal) {
-  const float3 tri_ctr = FaceCenter({tri.v0, tri.v1, tri.v2});
   const float3 nt = FaceNormal({tri.v0, tri.v1, tri.v2});
 
   // check if parallel
@@ -728,7 +725,7 @@ __device__ inline int BoxIntersections(
       }
     }
     // Update the face_verts_out tris
-    num_tris = offset;
+    num_tris = min(MAX_TRIS, offset);
     for (int j = 0; j < num_tris; ++j) {
       face_verts_out[j] = tri_verts_updated[j];
     }

pytorch3d/csrc/knn/knn.cu

@@ -338,7 +338,7 @@ std::tuple<at::Tensor, at::Tensor> KNearestNeighborIdxCuda(
 
   TORCH_CHECK((norm == 1) || (norm == 2), "Norm must be 1 or 2.");
 
-  TORCH_CHECK(p2.size(2) == D, "Point sets must have the same last dimension");
+  TORCH_CHECK(p1.size(2) == D, "Point sets must have the same last dimension");
   auto long_dtype = lengths1.options().dtype(at::kLong);
   auto idxs = at::zeros({N, P1, K}, long_dtype);
   auto dists = at::zeros({N, P1, K}, p1.options());
@@ -495,7 +495,7 @@ __global__ void KNearestNeighborBackwardKernel(
     if ((p1_idx < num1) && (k < num2)) {
       const float grad_dist = grad_dists[n * P1 * K + p1_idx * K + k];
       // index of point in p2 corresponding to the k-th nearest neighbor
-      const size_t p2_idx = idxs[n * P1 * K + p1_idx * K + k];
+      const int64_t p2_idx = idxs[n * P1 * K + p1_idx * K + k];
       // If the index is the pad value of -1 then ignore it
       if (p2_idx == -1) {
         continue;

pytorch3d/csrc/knn/knn.h

@@ -74,6 +74,8 @@ std::tuple<at::Tensor, at::Tensor> KNearestNeighborIdx(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(p1);
+  CHECK_CPU(p2);
   return KNearestNeighborIdxCpu(p1, p2, lengths1, lengths2, norm, K);
 }
 
@@ -140,6 +142,8 @@ std::tuple<at::Tensor, at::Tensor> KNearestNeighborBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(p1);
+  CHECK_CPU(p2);
   return KNearestNeighborBackwardCpu(
       p1, p2, lengths1, lengths2, idxs, norm, grad_dists);
 }

pytorch3d/csrc/marching_cubes/marching_cubes.cu

@@ -223,7 +223,7 @@ __global__ void CompactVoxelsKernel(
         compactedVoxelArray,
     const at::PackedTensorAccessor32<int, 1, at::RestrictPtrTraits>
         voxelOccupied,
-    const at::PackedTensorAccessor32<int, 1, at::RestrictPtrTraits>
+    const at::PackedTensorAccessor32<int64_t, 1, at::RestrictPtrTraits>
         voxelOccupiedScan,
     uint numVoxels) {
   uint id = blockIdx.x * blockDim.x + threadIdx.x;
@@ -255,7 +255,8 @@ __global__ void GenerateFacesKernel(
     at::PackedTensorAccessor<int64_t, 1, at::RestrictPtrTraits> ids,
     at::PackedTensorAccessor32<int, 1, at::RestrictPtrTraits>
         compactedVoxelArray,
-    at::PackedTensorAccessor32<int, 1, at::RestrictPtrTraits> numVertsScanned,
+    at::PackedTensorAccessor32<int64_t, 1, at::RestrictPtrTraits>
+        numVertsScanned,
     const uint activeVoxels,
     const at::PackedTensorAccessor32<float, 3, at::RestrictPtrTraits> vol,
     const at::PackedTensorAccessor32<int, 2, at::RestrictPtrTraits> faceTable,
@@ -381,6 +382,44 @@ __global__ void GenerateFacesKernel(
   } // end for grid-strided kernel
 }
 
+// ATen/Torch does not have an exclusive-scan operator. Additionally, in the
+// code below we need to get the "total number of items to work on" after
+// a scan, which with an inclusive-scan would simply be the value of the last
+// element in the tensor.
+//
+// This utility function hits two birds with one stone, by running
+// an inclusive-scan into a right-shifted view of a tensor that's
+// allocated to be one element bigger than the input tensor.
+//
+// Note; return tensor is `int64_t` per element, even if the input
+// tensor is only 32-bit. Also, the return tensor is one element bigger
+// than the input one.
+//
+// Secondary optional argument is an output argument that gets the
+// value of the last element of the return tensor (because you almost
+// always need this CPU-side right after this function anyway).
+static at::Tensor ExclusiveScanAndTotal(
+    const at::Tensor& inTensor,
+    int64_t* optTotal = nullptr) {
+  const auto inSize = inTensor.sizes()[0];
+  auto retTensor = at::zeros({inSize + 1}, at::kLong).to(inTensor.device());
+
+  using at::indexing::None;
+  using at::indexing::Slice;
+  auto rightShiftedView = retTensor.index({Slice(1, None)});
+
+  // Do an (inclusive-scan) cumulative sum in to the view that's
+  // shifted one element to the right...
+  at::cumsum_out(rightShiftedView, inTensor, 0, at::kLong);
+
+  if (optTotal) {
+    *optTotal = retTensor[inSize].cpu().item<int64_t>();
+  }
+
+  // ...so that the not-shifted tensor holds the exclusive-scan
+  return retTensor;
+}
+
 // Entrance for marching cubes cuda extension. Marching Cubes is an algorithm to
 // create triangle meshes from an implicit function (one of the form f(x, y, z)
 // = 0). It works by iteratively checking a grid of cubes superimposed over a
@@ -443,20 +482,18 @@ std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubesCuda(
   using at::indexing::Slice;
 
   auto d_voxelVerts =
-      at::zeros({numVoxels + 1}, at::TensorOptions().dtype(at::kInt))
+      at::zeros({numVoxels}, at::TensorOptions().dtype(at::kInt))
           .to(vol.device());
-  auto d_voxelVerts_ = d_voxelVerts.index({Slice(1, None)});
   auto d_voxelOccupied =
-      at::zeros({numVoxels + 1}, at::TensorOptions().dtype(at::kInt))
+      at::zeros({numVoxels}, at::TensorOptions().dtype(at::kInt))
           .to(vol.device());
-  auto d_voxelOccupied_ = d_voxelOccupied.index({Slice(1, None)});
 
   // Execute "ClassifyVoxelKernel" kernel to precompute
   // two arrays - d_voxelOccupied and d_voxelVertices to global memory,
   // which stores the occupancy state and number of voxel vertices per voxel.
   ClassifyVoxelKernel<<<grid, threads, 0, stream>>>(
-      d_voxelVerts_.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
+      d_voxelVerts.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
-      d_voxelOccupied_.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
+      d_voxelOccupied.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
       vol.packed_accessor32<float, 3, at::RestrictPtrTraits>(),
       isolevel);
   AT_CUDA_CHECK(cudaGetLastError());
@@ -466,12 +503,9 @@ std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubesCuda(
   // count for voxels in the grid and compute the number of active voxels.
   // If the number of active voxels is 0, return zero tensor for verts and
   // faces.
-
+  int64_t activeVoxels = 0;
-  auto d_voxelOccupiedScan = at::cumsum(d_voxelOccupied, 0);
+  auto d_voxelOccupiedScan =
-  auto d_voxelOccupiedScan_ = d_voxelOccupiedScan.index({Slice(1, None)});
+      ExclusiveScanAndTotal(d_voxelOccupied, &activeVoxels);
-
-  // number of active voxels
-  int activeVoxels = d_voxelOccupiedScan[numVoxels].cpu().item<int>();
 
   const int device_id = vol.device().index();
   auto opt = at::TensorOptions().dtype(at::kInt).device(at::kCUDA, device_id);
@@ -486,23 +520,21 @@ std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubesCuda(
     return std::make_tuple(verts, faces, ids);
   }
 
-  // Execute "CompactVoxelsKernel" kernel to compress voxels for accleration.
+  // Execute "CompactVoxelsKernel" kernel to compress voxels for acceleration.
   // This allows us to run triangle generation on only the occupied voxels.
   auto d_compVoxelArray = at::zeros({activeVoxels}, opt);
   CompactVoxelsKernel<<<grid, threads, 0, stream>>>(
       d_compVoxelArray.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
       d_voxelOccupied.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
-      d_voxelOccupiedScan_.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
+      d_voxelOccupiedScan
+          .packed_accessor32<int64_t, 1, at::RestrictPtrTraits>(),
       numVoxels);
   AT_CUDA_CHECK(cudaGetLastError());
   cudaDeviceSynchronize();
 
   // Scan d_voxelVerts array to generate offsets of vertices for each voxel
-  auto d_voxelVertsScan = at::cumsum(d_voxelVerts, 0);
+  int64_t totalVerts = 0;
-  auto d_voxelVertsScan_ = d_voxelVertsScan.index({Slice(1, None)});
+  auto d_voxelVertsScan = ExclusiveScanAndTotal(d_voxelVerts, &totalVerts);
-
-  // total number of vertices
-  int totalVerts = d_voxelVertsScan[numVoxels].cpu().item<int>();
 
   // Execute "GenerateFacesKernel" kernel
   // This runs only on the occupied voxels.
@@ -522,7 +554,7 @@ std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubesCuda(
       faces.packed_accessor<int64_t, 2, at::RestrictPtrTraits>(),
       ids.packed_accessor<int64_t, 1, at::RestrictPtrTraits>(),
       d_compVoxelArray.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
-      d_voxelVertsScan_.packed_accessor32<int, 1, at::RestrictPtrTraits>(),
+      d_voxelVertsScan.packed_accessor32<int64_t, 1, at::RestrictPtrTraits>(),
       activeVoxels,
       vol.packed_accessor32<float, 3, at::RestrictPtrTraits>(),
       faceTable.packed_accessor32<int, 2, at::RestrictPtrTraits>(),

pytorch3d/csrc/marching_cubes/marching_cubes.h

@@ -58,5 +58,6 @@ inline std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubes(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(vol);
   return MarchingCubesCpu(vol.contiguous(), isolevel);
 }

pytorch3d/csrc/marching_cubes/marching_cubes_cpu.cpp

@@ -71,8 +71,8 @@ std::tuple<at::Tensor, at::Tensor, at::Tensor> MarchingCubesCpu(
           if ((j + 1) % 3 == 0 && ps[0] != ps[1] && ps[1] != ps[2] &&
               ps[2] != ps[0]) {
             for (int k = 0; k < 3; k++) {
-              int v = tri[k];
+              int64_t v = tri.at(k);
-              edge_id_to_v[tri.at(k)] = ps.at(k);
+              edge_id_to_v[v] = ps.at(k);
               if (!uniq_edge_id.count(v)) {
                 uniq_edge_id[v] = verts.size();
                 verts.push_back(edge_id_to_v[v]);

pytorch3d/csrc/packed_to_padded_tensor/packed_to_padded_tensor.h

@@ -88,6 +88,8 @@ at::Tensor PackedToPadded(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(inputs_packed);
+  CHECK_CPU(first_idxs);
   return PackedToPaddedCpu(inputs_packed, first_idxs, max_size);
 }
 
@@ -105,5 +107,7 @@ at::Tensor PaddedToPacked(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(inputs_padded);
+  CHECK_CPU(first_idxs);
   return PaddedToPackedCpu(inputs_padded, first_idxs, num_inputs);
 }

pytorch3d/csrc/point_mesh/point_mesh_cpu.cpp

@@ -174,8 +174,8 @@ std::tuple<at::Tensor, at::Tensor> HullHullDistanceForwardCpu(
   at::Tensor idxs = at::zeros({A_N,}, as_first_idx.options());
   // clang-format on
 
-  auto as_a = as.accessor < float, H1 == 1 ? 2 : 3 > ();
+  auto as_a = as.accessor<float, H1 == 1 ? 2 : 3>();
-  auto bs_a = bs.accessor < float, H2 == 1 ? 2 : 3 > ();
+  auto bs_a = bs.accessor<float, H2 == 1 ? 2 : 3>();
   auto as_first_idx_a = as_first_idx.accessor<int64_t, 1>();
   auto bs_first_idx_a = bs_first_idx.accessor<int64_t, 1>();
   auto dists_a = dists.accessor<float, 1>();
@@ -230,10 +230,10 @@ std::tuple<at::Tensor, at::Tensor> HullHullDistanceBackwardCpu(
   at::Tensor grad_as = at::zeros_like(as);
   at::Tensor grad_bs = at::zeros_like(bs);
 
-  auto as_a = as.accessor < float, H1 == 1 ? 2 : 3 > ();
+  auto as_a = as.accessor<float, H1 == 1 ? 2 : 3>();
-  auto bs_a = bs.accessor < float, H2 == 1 ? 2 : 3 > ();
+  auto bs_a = bs.accessor<float, H2 == 1 ? 2 : 3>();
-  auto grad_as_a = grad_as.accessor < float, H1 == 1 ? 2 : 3 > ();
+  auto grad_as_a = grad_as.accessor<float, H1 == 1 ? 2 : 3>();
-  auto grad_bs_a = grad_bs.accessor < float, H2 == 1 ? 2 : 3 > ();
+  auto grad_bs_a = grad_bs.accessor<float, H2 == 1 ? 2 : 3>();
   auto idx_bs_a = idx_bs.accessor<int64_t, 1>();
   auto grad_dists_a = grad_dists.accessor<float, 1>();
 

pytorch3d/csrc/point_mesh/point_mesh_cuda.cu

@@ -110,7 +110,7 @@ __global__ void DistanceForwardKernel(
     __syncthreads();
 
     // Perform reduction in shared memory.
-    for (int s = blockDim.x / 2; s > 32; s >>= 1) {
+    for (auto s = blockDim.x / 2; s > 32; s >>= 1) {
       if (tid < s) {
         if (min_dists[tid] > min_dists[tid + s]) {
           min_dists[tid] = min_dists[tid + s];
@@ -502,8 +502,8 @@ __global__ void PointFaceArrayForwardKernel(
   const float3* tris_f3 = (float3*)tris;
 
   // Parallelize over P * S computations
-  const int num_threads = gridDim.x * blockDim.x;
+  const auto num_threads = gridDim.x * blockDim.x;
-  const int tid = blockIdx.x * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.x * blockDim.x + threadIdx.x;
 
   for (int t_i = tid; t_i < P * T; t_i += num_threads) {
     const int t = t_i / P; // segment index.
@@ -576,8 +576,8 @@ __global__ void PointFaceArrayBackwardKernel(
   const float3* tris_f3 = (float3*)tris;
 
   // Parallelize over P * S computations
-  const int num_threads = gridDim.x * blockDim.x;
+  const auto num_threads = gridDim.x * blockDim.x;
-  const int tid = blockIdx.x * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.x * blockDim.x + threadIdx.x;
 
   for (int t_i = tid; t_i < P * T; t_i += num_threads) {
     const int t = t_i / P; // triangle index.
@@ -683,8 +683,8 @@ __global__ void PointEdgeArrayForwardKernel(
   float3* segms_f3 = (float3*)segms;
 
   // Parallelize over P * S computations
-  const int num_threads = gridDim.x * blockDim.x;
+  const auto num_threads = gridDim.x * blockDim.x;
-  const int tid = blockIdx.x * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.x * blockDim.x + threadIdx.x;
 
   for (int t_i = tid; t_i < P * S; t_i += num_threads) {
     const int s = t_i / P; // segment index.
@@ -752,8 +752,8 @@ __global__ void PointEdgeArrayBackwardKernel(
   float3* segms_f3 = (float3*)segms;
 
   // Parallelize over P * S computations
-  const int num_threads = gridDim.x * blockDim.x;
+  const auto num_threads = gridDim.x * blockDim.x;
-  const int tid = blockIdx.x * blockDim.x + threadIdx.x;
+  const auto tid = blockIdx.x * blockDim.x + threadIdx.x;
 
   for (int t_i = tid; t_i < P * S; t_i += num_threads) {
     const int s = t_i / P; // segment index.

pytorch3d/csrc/point_mesh/point_mesh_cuda.h

@@ -88,6 +88,10 @@ std::tuple<torch::Tensor, torch::Tensor> PointFaceDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(points_first_idx);
+  CHECK_CPU(tris);
+  CHECK_CPU(tris_first_idx);
   return PointFaceDistanceForwardCpu(
       points, points_first_idx, tris, tris_first_idx, min_triangle_area);
 }
@@ -143,6 +147,10 @@ std::tuple<torch::Tensor, torch::Tensor> PointFaceDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(tris);
+  CHECK_CPU(idx_points);
+  CHECK_CPU(grad_dists);
   return PointFaceDistanceBackwardCpu(
       points, tris, idx_points, grad_dists, min_triangle_area);
 }
@@ -221,6 +229,10 @@ std::tuple<torch::Tensor, torch::Tensor> FacePointDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(points_first_idx);
+  CHECK_CPU(tris);
+  CHECK_CPU(tris_first_idx);
   return FacePointDistanceForwardCpu(
       points, points_first_idx, tris, tris_first_idx, min_triangle_area);
 }
@@ -277,6 +289,10 @@ std::tuple<torch::Tensor, torch::Tensor> FacePointDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(tris);
+  CHECK_CPU(idx_tris);
+  CHECK_CPU(grad_dists);
   return FacePointDistanceBackwardCpu(
       points, tris, idx_tris, grad_dists, min_triangle_area);
 }
@@ -346,6 +362,10 @@ std::tuple<torch::Tensor, torch::Tensor> PointEdgeDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(points_first_idx);
+  CHECK_CPU(segms);
+  CHECK_CPU(segms_first_idx);
   return PointEdgeDistanceForwardCpu(
       points, points_first_idx, segms, segms_first_idx, max_points);
 }
@@ -396,6 +416,10 @@ std::tuple<torch::Tensor, torch::Tensor> PointEdgeDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(segms);
+  CHECK_CPU(idx_points);
+  CHECK_CPU(grad_dists);
   return PointEdgeDistanceBackwardCpu(points, segms, idx_points, grad_dists);
 }
 
@@ -464,6 +488,10 @@ std::tuple<torch::Tensor, torch::Tensor> EdgePointDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(points_first_idx);
+  CHECK_CPU(segms);
+  CHECK_CPU(segms_first_idx);
   return EdgePointDistanceForwardCpu(
       points, points_first_idx, segms, segms_first_idx, max_segms);
 }
@@ -514,6 +542,10 @@ std::tuple<torch::Tensor, torch::Tensor> EdgePointDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(segms);
+  CHECK_CPU(idx_segms);
+  CHECK_CPU(grad_dists);
   return EdgePointDistanceBackwardCpu(points, segms, idx_segms, grad_dists);
 }
 
@@ -567,6 +599,8 @@ torch::Tensor PointFaceArrayDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(tris);
   return PointFaceArrayDistanceForwardCpu(points, tris, min_triangle_area);
 }
 
@@ -613,6 +647,9 @@ std::tuple<torch::Tensor, torch::Tensor> PointFaceArrayDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(tris);
+  CHECK_CPU(grad_dists);
   return PointFaceArrayDistanceBackwardCpu(
       points, tris, grad_dists, min_triangle_area);
 }
@@ -661,6 +698,8 @@ torch::Tensor PointEdgeArrayDistanceForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(segms);
   return PointEdgeArrayDistanceForwardCpu(points, segms);
 }
 
@@ -703,5 +742,8 @@ std::tuple<torch::Tensor, torch::Tensor> PointEdgeArrayDistanceBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points);
+  CHECK_CPU(segms);
+  CHECK_CPU(grad_dists);
   return PointEdgeArrayDistanceBackwardCpu(points, segms, grad_dists);
 }

pytorch3d/csrc/points_to_volumes/points_to_volumes.h

@@ -104,6 +104,12 @@ inline void PointsToVolumesForward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points_3d);
+  CHECK_CPU(points_features);
+  CHECK_CPU(volume_densities);
+  CHECK_CPU(volume_features);
+  CHECK_CPU(grid_sizes);
+  CHECK_CPU(mask);
   PointsToVolumesForwardCpu(
       points_3d,
       points_features,
@@ -183,6 +189,14 @@ inline void PointsToVolumesBackward(
     AT_ERROR("Not compiled with GPU support.");
 #endif
   }
+  CHECK_CPU(points_3d);
+  CHECK_CPU(points_features);
+  CHECK_CPU(grid_sizes);
+  CHECK_CPU(mask);
+  CHECK_CPU(grad_volume_densities);
+  CHECK_CPU(grad_volume_features);
+  CHECK_CPU(grad_points_3d);
+  CHECK_CPU(grad_points_features);
   PointsToVolumesBackwardCpu(
       points_3d,
       points_features,

pytorch3d/csrc/points_to_volumes/points_to_volumes_cpu.cpp

@@ -8,9 +8,7 @@
 
 #include <torch/csrc/autograd/VariableTypeUtils.h>
 #include <torch/extension.h>
-#include <algorithm>
 #include <cmath>
-#include <thread>
 #include <vector>
 
 // In the x direction, the location {0, ..., grid_size_x - 1} correspond to

pytorch3d/csrc/pulsar/global.h

@@ -15,8 +15,8 @@
 #endif
 
 #if defined(_WIN64) || defined(_WIN32)
-#define uint unsigned int
+using uint = unsigned int;
-#define ushort unsigned short
+using ushort = unsigned short;
 #endif
 
 #include "./logging.h" // <- include before torch/extension.h
@@ -30,11 +30,20 @@
 #define GLOBAL __global__
 #define RESTRICT __restrict__
 #define DEBUGBREAK()
+#ifdef __NVCC_DIAG_PRAGMA_SUPPORT__
+#pragma nv_diag_suppress 1866
+#pragma nv_diag_suppress 2941
+#pragma nv_diag_suppress 2951
+#pragma nv_diag_suppress 2967
+#else
+#if !defined(USE_ROCM)
 #pragma diag_suppress = attribute_not_allowed
 #pragma diag_suppress = 1866
 #pragma diag_suppress = 2941
 #pragma diag_suppress = 2951
 #pragma diag_suppress = 2967
+#endif //! USE_ROCM
+#endif
 #else // __CUDACC__
 #define INLINE inline
 #define HOST
@@ -49,6 +58,9 @@
 #pragma clang diagnostic pop
 #ifdef WITH_CUDA
 #include <ATen/cuda/CUDAContext.h>
+#if !defined(USE_ROCM)
+#include <vector_functions.h>
+#endif //! USE_ROCM
 #else
 #ifndef cudaStream_t
 typedef void* cudaStream_t;
@@ -65,8 +77,6 @@ struct float2 {
 struct float3 {
   float x, y, z;
 };
-#endif
-namespace py = pybind11;
 inline float3 make_float3(const float& x, const float& y, const float& z) {
   float3 res;
   res.x = x;
@@ -74,6 +84,8 @@ inline float3 make_float3(const float& x, const float& y, const float& z) {
   res.z = z;
   return res;
 }
+#endif
+namespace py = pybind11;
 
 inline bool operator==(const float3& a, const float3& b) {
   return a.x == b.x && a.y == b.y && a.z == b.z;

pytorch3d/csrc/pulsar/gpu/commands.h

@@ -59,6 +59,11 @@ getLastCudaError(const char* errorMessage, const char* file, const int line) {
 #define SHARED __shared__
 #define ACTIVEMASK() __activemask()
 #define BALLOT(mask, val) __ballot_sync((mask), val)
+
+/* TODO (ROCM-6.2): None of the WARP_* are used anywhere and ROCM-6.2 natively
+ * supports __shfl_*. Disabling until the move to ROCM-6.2.
+ */
+#if !defined(USE_ROCM)
 /**
  * Find the cumulative sum within a warp up to the current
  * thread lane, with each mask thread contributing base.
@@ -115,6 +120,7 @@ INLINE DEVICE float3 WARP_SUM_FLOAT3(
   ret.z = WARP_SUM(group, mask, base.z);
   return ret;
 }
+#endif //! USE_ROCM
 
 // Floating point.
 // #define FMUL(a, b) __fmul_rn((a), (b))
@@ -142,6 +148,7 @@ INLINE DEVICE float3 WARP_SUM_FLOAT3(
 #define FMA(x, y, z) __fmaf_rn((x), (y), (z))
 #define I2F(a) __int2float_rn(a)
 #define FRCP(x) __frcp_rn(x)
+#if !defined(USE_ROCM)
 __device__ static float atomicMax(float* address, float val) {
   int* address_as_i = (int*)address;
   int old = *address_as_i, assumed;
@@ -166,6 +173,7 @@ __device__ static float atomicMin(float* address, float val) {
   } while (assumed != old);
   return __int_as_float(old);
 }
+#endif //! USE_ROCM
 #define DMAX(a, b) FMAX(a, b)
 #define DMIN(a, b) FMIN(a, b)
 #define DSQRT(a) sqrt(a)
@@ -409,7 +417,7 @@ __device__ static float atomicMin(float* address, float val) {
       (OUT_PTR),              \
       (NUM_SELECTED_PTR),     \
       (NUM_ITEMS),            \
-      stream = (STREAM));
+      (STREAM));
 
 #define COPY_HOST_DEV(PTR_D, PTR_H, TYPE, SIZE) \
   HANDLECUDA(cudaMemcpy(                        \