3d-Object-Classification-using-PointNet/point_net_model.py at main · ankitVP77/3d-Object-Classification-using-PointNet · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np

class Spatial3d(nn.Module):
    """
    Spatial Transformer Network.
    """
    def __init__(self, num_points = 2500):
        super().__init__()
        self.num_points = num_points
        self.conv1 = torch.nn.Conv1d(3, 64, 1)
        self.conv2 = torch.nn.Conv1d(64, 128, 1)
        self.conv3 = torch.nn.Conv1d(128, 1024, 1)
        self.mp1 = torch.nn.MaxPool1d(num_points)
        self.fc1 = nn.Linear(1024, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, 9)
        self.relu = nn.ReLU()

        self.bn1 = nn.BatchNorm1d(64)
        self.bn2 = nn.BatchNorm1d(128)
        self.bn3 = nn.BatchNorm1d(1024)
        self.bn4 = nn.BatchNorm1d(512)
        self.bn5 = nn.BatchNorm1d(256)


    def forward(self, x):
        batchsize = x.size()[0]
        x = F.relu(self.bn1(self.conv1(x)))
        x = F.relu(self.bn2(self.conv2(x)))
        x = F.relu(self.bn3(self.conv3(x)))
        x = self.mp1(x)
        x = x.view(-1, 1024)

        x = F.relu(self.bn4(self.fc1(x)))
        x = F.relu(self.bn5(self.fc2(x)))
        x = self.fc3(x)

        iden = Variable(torch.from_numpy(np.array([1,0,0,0,1,0,0,0,1]).astype(np.float32))).view(1,9).repeat(batchsize,1)
        if x.is_cuda:
            iden = iden.cuda()
        x = x + iden
        x = x.view(-1, 3, 3)
        return x


class PointNetfeat(nn.Module):
    """
    This is the T-Net for Feature Transform.
    """
    def __init__(self, num_points=2500, global_feat=True):
        super(PointNetfeat, self).__init__()
        self.stn = Spatial3d(num_points=num_points)
        self.conv1 = torch.nn.Conv1d(3, 64, 1)
        self.conv2 = torch.nn.Conv1d(64, 128, 1)
        self.conv3 = torch.nn.Conv1d(128, 1024, 1)
        self.bn1 = nn.BatchNorm1d(64)
        self.bn2 = nn.BatchNorm1d(128)
        self.bn3 = nn.BatchNorm1d(1024)
        self.mp1 = torch.nn.MaxPool1d(num_points)
        self.num_points = num_points
        self.global_feat = global_feat

    def forward(self, x):
        trans = self.stn(x)
        x = x.transpose(2, 1)
        x = torch.bmm(x, trans)
        x = x.transpose(2, 1)
        x = F.relu(self.bn1(self.conv1(x)))
        pointfeat = x
        x = F.relu(self.bn2(self.conv2(x)))
        x = self.bn3(self.conv3(x))
        x = self.mp1(x)
        x = x.view(-1, 1024)
        if self.global_feat:
            return x, trans
        else:
            x = x.view(-1, 1024, 1).repeat(1, 1, self.num_points)
            return torch.cat([x, pointfeat], 1), trans

class PointNet(nn.Module):
    """
    Network for Classification
    """
    def __init__(self, num_points = 2500, k = 2):
        super(PointNet, self).__init__()
        self.num_points = num_points
        self.feat = PointNetfeat(num_points, global_feat=True)
        self.fc1 = nn.Linear(1024, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, k)
        self.bn1 = nn.BatchNorm1d(512)
        self.bn2 = nn.BatchNorm1d(256)
        self.relu = nn.ReLU()
    def forward(self, x):
        x, trans = self.feat(x)
        x = F.relu(self.bn1(self.fc1(x)))
        x = F.relu(self.bn2(self.fc2(x)))
        x = self.fc3(x)
        return F.log_softmax(x, dim=-1), trans