pynif3d.renderer¶

class pynif3d.renderer.PointRenderer(chunk_size=None)¶

Bases: torch.nn.modules.module.Module

The function that is used for rendering each sampled point using the NIF model.

Usage:

# Assume that a NIF model (torch.nn.Module) is given.
renderer = PointRenderer(chunk_size=256)
prediction = renderer(nif_model)

Parameters: chunk_size (int) – The chunk size of the tensor that is passed for NIF prediction.

forward(nif_model, *args)¶

Parameters

nif_model (torch.nn.Module) – NIF model for outputting the prediction.
args (list, tuple) – Tuple or list containing the tensors that are passed through the NIF model.

Returns

Tensor containing the concatenated predictions.

Return type

torch.Tensor