def __init__(self, num_classes, normal_channel=False):
super(get_model, self).__init__()
if normal_channel:
additional_channel = 3
else:
additional_channel = 0
self.normal_channel = normal_channel
self.sa1 = PointNetSetAbstraction(npoint=512,
radius=0.2,
nsample=32,
in_channel=6 + additional_channel,
mlp=[64, 64, 128],
group_all=False)
self.sa2 = PointNetSetAbstraction(npoint=128,
radius=0.4,
nsample=64,
in_channel=128 + 3,
mlp=[128, 128, 256],
group_all=False)
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=256 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fp3 = PointNetFeaturePropagation(in_channel=1280, mlp=[256, 256])
self.fp2 = PointNetFeaturePropagation(in_channel=384, mlp=[256, 128])
self.fp1 = PointNetFeaturePropagation(in_channel=128 + 16 + 6 +
additional_channel,
mlp=[128, 128, 128])
self.conv1 = nn.Conv1d(128, 128, 1)
self.bn1 = nn.BatchNorm1d(128)
self.drop1 = nn.Dropout(0.5)
self.conv2 = nn.Conv1d(128, num_classes, 1)
def __init__(self, num_class, normal_channel=False):
super(get_model, self).__init__()
in_channel = 6 if normal_channel else 3
self.normal_channel = normal_channel
# TODO adapt the group numbers (npoint)
self.sa1 = PointNetSetAbstraction(npoint=32,
radius=0.2,
nsample=4,
in_channel=in_channel,
mlp=[64, 64, 128],
group_all=False)
self.sa2 = PointNetSetAbstraction(npoint=16,
radius=0.4,
nsample=8,
in_channel=128 + 3,
mlp=[128, 128, 256],
group_all=False)
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=256 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fc1 = nn.Linear(1024, 512)
self.bn1 = nn.BatchNorm1d(512)
self.drop1 = nn.Dropout(0.4)
self.fc2 = nn.Linear(512, 256)
self.bn2 = nn.BatchNorm1d(256)
self.drop2 = nn.Dropout(0.4)
self.fc3 = nn.Linear(256, num_class)
def __init__(self, num_classes):
super(PointNet2PartSeg, self).__init__()
self.sa1 = PointNetSetAbstraction(npoint=512,
radius=0.2,
nsample=64,
in_channel=3,
mlp=[64, 64, 128],
group_all=False)
self.sa2 = PointNetSetAbstraction(npoint=128,
radius=0.4,
nsample=64,
in_channel=128 + 3,
mlp=[128, 128, 256],
group_all=False)
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=256 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fp3 = PointNetFeaturePropagation(in_channel=1280, mlp=[256, 256])
self.fp2 = PointNetFeaturePropagation(in_channel=384, mlp=[256, 128])
self.fp1 = PointNetFeaturePropagation(in_channel=128,
mlp=[128, 128, 128])
self.conv1 = nn.Conv1d(128, 128, 1)
self.bn1 = nn.BatchNorm1d(128)
self.drop1 = nn.Dropout(0.5)
self.conv2 = nn.Conv1d(128, num_classes, 1)
def __init__(self, num_classes=40):
super(PointNet2ClsSsg, self).__init__()
self.sa1 = PointNetSetAbstraction(npoint=512,
radius=0.2,
nsample=32,
in_channel=3,
mlp=[64, 64, 128],
group_all=False)
self.sa2 = PointNetSetAbstraction(npoint=128,
radius=0.4,
nsample=64,
in_channel=128 + 3,
mlp=[128, 128, 256],
group_all=False)
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=256 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fc1 = nn.Linear(1024, 512)
self.bn1 = nn.BatchNorm1d(512)
self.drop1 = nn.Dropout(0.4)
self.fc2 = nn.Linear(512, 256)
self.bn2 = nn.BatchNorm1d(256)
self.drop2 = nn.Dropout(0.4)
self.fc3 = nn.Linear(256, num_classes)
def __init__(self, num_classes, normal_channel=False):
super(get_model, self).__init__()
if normal_channel:
additional_channel = 3
else:
additional_channel = 0
self.normal_channel = normal_channel
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [32, 64, 128], 3 + additional_channel,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.4, 0.8], [64, 128], 128 + 128 + 64,
[[128, 128, 256], [128, 196, 256]])
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=512 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fp3 = PointNetFeaturePropagation(in_channel=1536, mlp=[256, 256])
self.fp2 = PointNetFeaturePropagation(in_channel=576, mlp=[256, 128])
self.fp1 = PointNetFeaturePropagation(in_channel=150 +
additional_channel,
mlp=[128, 128])
self.conv1 = nn.Conv1d(128, 128, 1)
self.bn1 = nn.BatchNorm1d(128)
self.drop1 = nn.Dropout(0.5)
self.conv2 = nn.Conv1d(128, num_classes, 1)
def __init__(self,
num_class,
num_points,
normal_channel=False,
decoder=False):
super(get_model, self).__init__()
in_channel = 3 if normal_channel else 0
self.normal_channel = normal_channel
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [16, 32, 128], in_channel,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.2, 0.4, 0.8], [32, 64, 128], 320,
[[64, 64, 128], [128, 128, 256], [128, 128, 256]])
self.sa3 = PointNetSetAbstraction(None, None, None, 640 + 3,
[256, 512, 1024], True)
self.fc1 = nn.Linear(1024, 512)
self.bn1 = nn.BatchNorm1d(512)
self.drop1 = nn.Dropout(0.4)
self.fc2 = nn.Linear(512, 256)
self.bn2 = nn.BatchNorm1d(256)
self.drop2 = nn.Dropout(0.5)
self.fc3 = nn.Linear(256, num_class)
self.decode = decoder
if self.decode:
self.decoder = PointDecoder(num_points)
def __init__(self, num_classes):
super(get_model, self).__init__()
self.sa1 = PointNetSetAbstraction(1024, 0.1, 32, 8, [32, 32, 64],
False)
self.sa2 = PointNetSetAbstraction(256, 0.2, 32, 64 + 3, [64, 64, 128],
False)
self.sa3 = PointNetSetAbstraction(64, 0.4, 32, 128 + 3,
[128, 128, 256], False)
self.sa4 = PointNetSetAbstraction(16, 0.8, 32, 256 + 3,
[256, 256, 512], False)
self.fp4 = PointNetFeaturePropagation(768, [256, 256])
self.fp3 = PointNetFeaturePropagation(384, [256, 256])
self.fp2 = PointNetFeaturePropagation(320, [256, 128])
self.fp1 = PointNetFeaturePropagation(128, [128, 128, 128])
self.conv1 = nn.Conv1d(128, 128, 1)
self.bn1 = nn.BatchNorm1d(128)
self.drop1 = nn.Dropout(0.5)
self.conv2 = nn.Conv1d(128, num_classes, 1)
def __init__(self, num_class, normal_channel=True):
super(get_encoder_model, self).__init__()
in_channel = 3 if normal_channel else 0
self.normal_channel = normal_channel
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [16, 32, 128], in_channel,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.2, 0.4, 0.8], [32, 64, 128], 320,
[[64, 64, 128], [128, 128, 256], [128, 128, 256]])
self.sa3 = PointNetSetAbstraction(None, None, None, 640 + 3,
[256, 512, 1024], True)
self.fc1 = nn.Linear(1024, 512)
def __init__(self, num_classes=40):
super(PointNet2ClsMsg, self).__init__()
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [16, 32, 128], 0,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.2, 0.4, 0.8], [32, 64, 128], 320,
[[64, 64, 128], [128, 128, 256], [128, 128, 256]])
self.sa3 = PointNetSetAbstraction(None, None, None, 640 + 3,
[256, 512, 1024], True)
self.fc1 = nn.Linear(1024, 512)
self.bn1 = nn.BatchNorm1d(512)
self.drop1 = nn.Dropout(0.4)
self.fc2 = nn.Linear(512, 256)
self.bn2 = nn.BatchNorm1d(256)
self.drop2 = nn.Dropout(0.4)
self.fc3 = nn.Linear(256, num_classes)
def __init__(self, num_classes):
super(PointNet2PartSeg_msg_one_hot, self).__init__()
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [32, 64, 128], 0 + 3,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.4, 0.8], [64, 128], 128 + 128 + 64,
[[128, 128, 256], [128, 196, 256]])
self.sa3 = PointNetSetAbstraction(npoint=None,
radius=None,
nsample=None,
in_channel=512 + 3,
mlp=[256, 512, 1024],
group_all=True)
self.fp3 = PointNetFeaturePropagation(in_channel=1536, mlp=[256, 256])
self.fp2 = PointNetFeaturePropagation(in_channel=576, mlp=[256, 128])
self.fp1 = PointNetFeaturePropagation(in_channel=150, mlp=[128, 128])
self.conv1 = nn.Conv1d(128, 128, 1)
self.bn1 = nn.BatchNorm1d(128)
self.drop1 = nn.Dropout(0.5)
self.conv2 = nn.Conv1d(128, num_classes, 1)
def __init__(self, num_class, num_point, num_channel): super(get_model, self).__init__() self.sa1 = PointNetSetAbstraction(num_point, 0.1, 32, 3 + 3, [32, 32, 64], False) self.sa2 = PointNetSetAbstraction(256, 0.2, 32, 64 + 3, [64, 64, 128], False) self.sa3 = PointNetSetAbstraction(64, 0.4, 32, 128 + 3, [128, 128, 256], False) self.sa4 = PointNetSetAbstraction(16, 0.8, 32, 256 + 3, [256, 256, 512], False) self.fp4 = PointNetFeaturePropagation(768, [256, 256]) self.fp3 = PointNetFeaturePropagation(384, [256, 256]) self.fp2 = PointNetFeaturePropagation(320, [256, 128]) self.fp1 = PointNetFeaturePropagation(128, [128, 128, 128]) self.sa_other_1 = PointNetSetAbstraction(num_point, 0.1, 32, num_channel - 3, [32, 32, 64], False, concat_norm_xyz = False) self.sa_other_2 = PointNetSetAbstraction(256, 0.2, 32, 64, [64, 64, 128], False, concat_norm_xyz = False) self.sa_other_3 = PointNetSetAbstraction(64, 0.4, 32, 128, [128, 128, 256], False, concat_norm_xyz = False) self.sa_other_4 = PointNetSetAbstraction(16, 0.8, 32, 256, [256, 256, 512], False, concat_norm_xyz = False) self.fp_other_4 = PointNetFeaturePropagation(768, [256, 256]) self.fp_other_3 = PointNetFeaturePropagation(384, [256, 256]) self.fp_other_2 = PointNetFeaturePropagation(320, [256, 128]) self.fp_other_1 = PointNetFeaturePropagation(128, [128, 128, 128]) self.conv1 = nn.Conv1d(256, 256, 1) self.bn1 = nn.BatchNorm1d(256) self.drop1 = nn.Dropout(0.5) self.conv2 = nn.Conv1d(256, num_class, 1)
def __init__(self, num_class, normal_channel=True):
super(get_model, self).__init__()
in_channel = 3 if normal_channel else 0
self.normal_channel = normal_channel
self.sa1 = PointNetSetAbstractionMsg(
512, [0.1, 0.2, 0.4], [16, 32, 128], in_channel,
[[32, 32, 64], [64, 64, 128], [64, 96, 128]])
self.sa2 = PointNetSetAbstractionMsg(
128, [0.2, 0.4, 0.8], [32, 64, 128], 320,
[[64, 64, 128], [128, 128, 256], [128, 128, 256]])
self.sa3 = PointNetSetAbstraction(None, None, None, 640 + 3,
[256, 512, 1024], True)
self.fc1 = nn.Linear(1024, 512)
self.bn1 = nn.BatchNorm1d(512)
self.drop1 = nn.Dropout(0.4)
self.fc2 = nn.Linear(512, 256)
self.bn2 = nn.BatchNorm1d(256)
self.drop2 = nn.Dropout(0.5)
# self.fc3 = nn.Linear(256, 40)
# self.encoder = torch.nn.Sequential(*list(self.children())[:-1])
self.projetion = MLPHead(in_channels=256,
mlp_hidden_size=512,
projection_size=128)