torchdrivesim.rendering.nvdiffrast¶

Nvdiffrast-based renderers, equivalent to those based on PyTorch3D but sometimes faster. This module imports correctly if nvdiffrast is missing, but the renderer will raise the NvdiffrastNotFound exception.

Attributes¶

`is_available`
`logger`
`glctx_sessions`

Exceptions¶

NvdiffrastNotFound

Nvdiffrast is not installed.

Classes¶

`NvdiffrastRendererConfig`	Configuration of nvdiffrast-based renderer.
`NvdiffrastRenderer`	Similar to PyTorch3DRenderer, and producing indistinguishable images, but sometimes faster.

Functions¶

get_glctx_session(device[, opengl])

Module Contents¶

torchdrivesim.rendering.nvdiffrast.is_available = True[source]¶

torchdrivesim.rendering.nvdiffrast.logger = None[source]¶

torchdrivesim.rendering.nvdiffrast.glctx_sessions[source]¶

exception torchdrivesim.rendering.nvdiffrast.NvdiffrastNotFound[source]¶

Bases: ImportError

Nvdiffrast is not installed.

torchdrivesim.rendering.nvdiffrast.get_glctx_session(device, opengl=True)[source]¶

class torchdrivesim.rendering.nvdiffrast.NvdiffrastRendererConfig[source]¶

Bases: torchdrivesim.rendering.base.RendererConfig

Configuration of nvdiffrast-based renderer.

backend: str = 'nvdiffrast'[source]¶

antialias: bool = False[source]¶

opengl: bool = False[source]¶

max_minibatch_size: int | None = None[source]¶

class torchdrivesim.rendering.nvdiffrast.NvdiffrastRenderer(cfg: NvdiffrastRendererConfig, *args, **kwargs)[source]¶

Bases: torchdrivesim.rendering.base.BirdviewRenderer

Similar to PyTorch3DRenderer, and producing indistinguishable images, but sometimes faster. Note that nvdiffrast requires separate installation and is subject to its own license terms.

cfg: NvdiffrastRendererConfig[source]¶

glctx = None[source]¶

render_rgb_mesh(mesh: torchdrivesim.mesh.RGBMesh, res: torchdrivesim.utils.Resolution, cameras: torchdrivesim.rendering.base.Cameras) → torch.Tensor[source]¶: Renders a given mesh, producing BxHxWxC tensor image of float RGB values in [0,255] range.