fastdev.nn.pointnet2

PointNet++ implementation in PyTorch.

Adapted from: https://github.com/yanx27/Pointnet_Pointnet2_pytorch

Module Contents

class fastdev.nn.pointnet2.PointNet2Encoder(normal_channel: bool = False, feature_dim: int = 1024, n_points: Tuple[int, int] = (512, 128), n_samples: Tuple[int, int] = (32, 64), radius: Tuple[float, float] = (0.2, 0.4))

Bases: torch.nn.Module

Parameters:

• normal_channel (bool)

• feature_dim (int)

• n_points (Tuple[int, int])

• n_samples (Tuple[int, int])

• radius (Tuple[float, float])

normal_channel = False

sa1

sa2

sa3

forward(xyz)

class fastdev.nn.pointnet2.PointNet2Cls(num_class: int, normal_channel=True)

Bases: torch.nn.Module

Parameters:

num_class (int)

normal_channel = True

sa1

sa2

sa3

fc1

bn1

drop1

fc2

bn2

drop2

fc3

relu

forward(xyz)