Driver update for ci, easier diagnosing

Summary: Bump the nvidia driver used in the conda tests. Add an environment variable (unused) to allow building without ninja. Print relative error on assertClose failure.

Reviewed By: nikhilaravi

Differential Revision: D21227373

fbshipit-source-id: 5dd8eb097151da27d3632daa755a1e7b9ac97845

Author: bottler

.circleci/config.in.yml

@@ -157,7 +157,7 @@ jobs:
           sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit=${NVIDIA_CONTAINER_VERSION}
           sudo systemctl restart docker
 
-          DRIVER_FN="NVIDIA-Linux-x86_64-410.104.run"
+          DRIVER_FN="NVIDIA-Linux-x86_64-440.59.run"
           wget "https://s3.amazonaws.com/ossci-linux/nvidia_driver/$DRIVER_FN"
           sudo /bin/bash "$DRIVER_FN" -s --no-drm || (sudo cat /var/log/nvidia-installer.log && false)
           nvidia-smi

.circleci/config.yml

@@ -157,7 +157,7 @@ jobs:
           sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit=${NVIDIA_CONTAINER_VERSION}
           sudo systemctl restart docker
 
-          DRIVER_FN="NVIDIA-Linux-x86_64-410.104.run"
+          DRIVER_FN="NVIDIA-Linux-x86_64-440.59.run"
           wget "https://s3.amazonaws.com/ossci-linux/nvidia_driver/$DRIVER_FN"
           sudo /bin/bash "$DRIVER_FN" -s --no-drm || (sudo cat /var/log/nvidia-installer.log && false)
           nvidia-smi

pytorch3d/io/mtl_io.py

@@ -62,7 +62,7 @@ def make_mesh_texture_atlas(
         # the convention GL_REPEAT in OpenGL i.e the integer part of the coordinate
         # will be ignored and a repeating pattern is formed.
         # Shapenet data uses this format see:
-        # https://shapenet.org/qaforum/index.php?qa=15&qa_1=why-is-the-texture-coordinate-in-the-obj-file-not-in-the-range
+        # https://shapenet.org/qaforum/index.php?qa=15&qa_1=why-is-the-texture-coordinate-in-the-obj-file-not-in-the-range # noqa: B950
         if (faces_verts_uvs > 1).any() or (faces_verts_uvs < 0).any():
             msg = "Texture UV coordinates outside the range [0, 1]. \
                 The integer part will be ignored to form a repeating pattern."

setup.py

@@ -72,6 +72,18 @@ def get_extensions():
 with open("pytorch3d/__init__.py", "r") as init:
     exec(init.read())
 
+
+if os.getenv("PYTORCH3D_NO_NINJA", "0") == "1":
+
+    class BuildExtension(torch.utils.cpp_extension.BuildExtension):
+        def __init__(self, *args, **kwargs):
+            super().__init__(use_ninja=False, *args, **kwargs)
+
+
+else:
+    BuildExtension = torch.utils.cpp_extension.BuildExtension
+
+
 setup(
     name="pytorch3d",
     version=__version__,
@@ -86,5 +98,5 @@ def get_extensions():
         "dev": ["flake8", "isort", "black==19.3b0"],
     },
     ext_modules=get_extensions(),
-    cmdclass={"build_ext": torch.utils.cpp_extension.BuildExtension},
+    cmdclass={"build_ext": BuildExtension},
 )

tests/common_testing.py

@@ -138,7 +138,19 @@ def assertClose(
         )
 
         if not close and msg is None:
-            max_diff = backend.abs(input - other).max()
-            self.fail(f"Not close. max diff {max_diff}.")
+            diff = backend.abs(input - other) + 0.0
+            ratio = diff / backend.abs(other)
+            try_relative = (diff <= atol) | (backend.isfinite(ratio) & (ratio > 0))
+            if try_relative.all():
+                if backend == np:
+                    # Avoid a weirdness with zero dimensional arrays.
+                    ratio = np.array(ratio)
+                ratio[diff <= atol] = 0
+                extra = f" Max relative diff {ratio.max()}"
+            else:
+                extra = ""
+            shape = tuple(input.shape)
+            max_diff = diff.max()
+            self.fail(f"Not close. Max diff {max_diff}.{extra} Shape {shape}.")
 
         self.assertTrue(close, msg)