stratified_sampling argument: set default to None (#1324)

Summary:
The self._stratified_sampling attribute is always overridden unless stratified_sampling is explicitly set to None. However, the desired default behavior is that the value of self._stratified_sampling is used unless the argument stratified_sampling is set to True/False. Changing the default to None achieves this

Pull Request resolved: https://github.com/facebookresearch/pytorch3d/pull/1324

Reviewed By: bottler

Differential Revision: D39259775

Pulled By: davnov134

fbshipit-source-id: e01bb747ac80c812eb27bf22e67f5e14f29acadd

pytorch3d/renderer/implicit/raysampling.py

@@ -124,7 +124,7 @@ class MultinomialRaysampler(torch.nn.Module):
         max_depth: Optional[float] = None,
         n_rays_per_image: Optional[int] = None,
         n_pts_per_ray: Optional[int] = None,
-        stratified_sampling: bool = False,
+        stratified_sampling: Optional[bool] = None,
         **kwargs,
     ) -> RayBundle:
         """
@@ -313,7 +313,11 @@ class MonteCarloRaysampler(torch.nn.Module):
         self._stratified_sampling = stratified_sampling
 
     def forward(
-        self, cameras: CamerasBase, *, stratified_sampling: bool = False, **kwargs
+        self,
+        cameras: CamerasBase,
+        *,
+        stratified_sampling: Optional[bool] = None,
+        **kwargs,
     ) -> RayBundle:
         """
         Args: