Method forward

models/backbone_module.py:83–133 · view source on GitHub ↗

r""" Forward pass of the network Parameters ---------- pointcloud: Variable(torch.cuda.FloatTensor) (B, N, 3 + input_feature_dim) tensor Point cloud to run predicts on Each point in the point-cloud MUST

(self, pointcloud: torch.cuda.FloatTensor, end_points=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

_break_up_pcMethod · 0.95

Tested by

no test coverage detected