-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmodels.py
197 lines (165 loc) · 7.28 KB
/
models.py
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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
import os
import sys
import copy
import math
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
class Tnet(nn.Module): #Tnet parts (3*3 and 64*64) of pointnet architecture
def __init__(self, k=3):
super().__init__()
self.k=k
self.conv1 = nn.Conv1d(k,64,1)
self.conv2 = nn.Conv1d(64,128,1)
self.conv3 = nn.Conv1d(128,1024,1)
self.fc1 = nn.Linear(1024,512)
self.fc2 = nn.Linear(512,256)
self.fc3 = nn.Linear(256,k*k)
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, input):
bs = input.size(0)
xb = F.relu(self.bn1(self.conv1(input)))
xb = F.relu(self.bn2(self.conv2(xb)))
xb = F.relu(self.bn3(self.conv3(xb)))
xb = torch.max(xb, 2, keepdim=True)[0]
xb = xb.view(-1,1024)
xb = F.relu(self.bn4(self.fc1(xb)))
xb = F.relu(self.bn5(self.fc2(xb)))
#initialize as identity
init = torch.eye(self.k, requires_grad=True).repeat(bs,1,1)
if xb.is_cuda:
init=init.cuda()
matrix = self.fc3(xb).view(-1,self.k,self.k) + init
return matrix
class Transform(nn.Module):
def __init__(self):
super().__init__()
self.input_transform = Tnet(k=3)
self.feature_transform = Tnet(k=64)
self.conv1 = nn.Conv1d(3,64,1)
self.conv2 = nn.Conv1d(64,128,1)
self.conv3 = nn.Conv1d(128,1024,1)
self.bn1 = nn.BatchNorm1d(64)
self.bn2 = nn.BatchNorm1d(128)
self.bn3 = nn.BatchNorm1d(1024)
def forward(self, input, x):
if x == True:
matrix3x3 = self.input_transform(input)
xb = torch.bmm(torch.transpose(input,1,2), matrix3x3).transpose(1,2)
xb = F.relu(self.bn1(self.conv1(xb)))
matrix64x64 = self.feature_transform(xb)
xb = torch.bmm(torch.transpose(xb,1,2), matrix64x64).transpose(1,2)
else:
xb = F.relu(self.bn1(self.conv1(input)))
matrix3x3 = torch.zeros(32,3,3)
matrix64x64 = torch.zeros(32,64,64)
xb = F.relu(self.bn2(self.conv2(xb)))
xb = self.bn3(self.conv3(xb))
xb = nn.MaxPool1d(xb.size(-1))(xb)
output = nn.Flatten(1)(xb)
return output, matrix3x3, matrix64x64
class PointNet(nn.Module): #PointNet classification architecture
def __init__(self, classes = 10):
super().__init__()
self.transform = Transform()
self.fc1 = nn.Linear(1024, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, classes)
self.dropout = nn.Dropout(p=0.4)
self.bn1 = nn.BatchNorm1d(512)
self.bn2 = nn.BatchNorm1d(256)
#self.dropout = nn.Dropout(p=0.3)
self.logsoftmax = nn.LogSoftmax(dim=1)
def forward(self, input, x):
xb, matrix3x3, matrix64x64 = self.transform(input, x)
xb = F.relu(self.bn1(self.fc1(xb)))
xb = F.relu(self.bn2(self.dropout(self.fc2(xb))))
output = self.fc3(xb)
return self.logsoftmax(output), matrix3x3, matrix64x64
def knn(x, k): #Calculate K nearest neighbors for DGCNN Network
inner = -2*torch.matmul(x.transpose(2, 1), x)
xx = torch.sum(x**2, dim=1, keepdim=True)
pairwise_distance = -xx - inner - xx.transpose(2, 1)
idx = pairwise_distance.topk(k=k, dim=-1)[1] # (batch_size, num_points, k)
return idx
def get_graph_feature(x, k=20, idx=None):
batch_size = x.size(0)
num_points = x.size(2)
x = x.view(batch_size, -1, num_points)
if idx is None:
idx = knn(x, k=k) # (batch_size, num_points, k)
device = torch.device('cuda')
idx_base = torch.arange(0, batch_size, device=device).view(-1, 1, 1)*num_points
idx = idx + idx_base
idx = idx.view(-1)
_, num_dims, _ = x.size()
x = x.transpose(2, 1).contiguous() # (batch_size, num_points, num_dims) -> (batch_size*num_points, num_dims) # batch_size * num_points * k + range(0, batch_size*num_points)
feature = x.view(batch_size*num_points, -1)[idx, :]
feature = feature.view(batch_size, num_points, k, num_dims)
x = x.view(batch_size, num_points, 1, num_dims).repeat(1, 1, k, 1)
feature = torch.cat((feature-x, x), dim=3).permute(0, 3, 1, 2).contiguous()
return feature
class DGCNN(nn.Module): #DGCNN architecture
def __init__(self,output_channels=10):
super(DGCNN, self).__init__()
# self.args = args
self.k = 20
self.bn1 = nn.BatchNorm2d(64)
self.bn2 = nn.BatchNorm2d(64)
self.bn3 = nn.BatchNorm2d(128)
self.bn4 = nn.BatchNorm2d(256)
self.bn5 = nn.BatchNorm1d(1024)
self.conv1 = nn.Sequential(nn.Conv2d(6, 64, kernel_size=1, bias=False),
self.bn1,
nn.LeakyReLU(negative_slope=0.2))
self.conv2 = nn.Sequential(nn.Conv2d(64*2, 64, kernel_size=1, bias=False),
self.bn2,
nn.LeakyReLU(negative_slope=0.2))
self.conv3 = nn.Sequential(nn.Conv2d(64*2, 128, kernel_size=1, bias=False),
self.bn3,
nn.LeakyReLU(negative_slope=0.2))
self.conv4 = nn.Sequential(nn.Conv2d(128*2, 256, kernel_size=1, bias=False),
self.bn4,
nn.LeakyReLU(negative_slope=0.2))
self.conv5 = nn.Sequential(nn.Conv1d(512, 1024, kernel_size=1, bias=False),
self.bn5,
nn.LeakyReLU(negative_slope=0.2))
self.linear1 = nn.Linear(1024*2, 512, bias=False)
self.bn6 = nn.BatchNorm1d(512)
self.dp1 = nn.Dropout(p=0.5)
self.linear2 = nn.Linear(512, 256)
self.bn7 = nn.BatchNorm1d(256)
self.dp2 = nn.Dropout(p=0.5)
self.linear3 = nn.Linear(256, output_channels)
self.logsoftmax = nn.LogSoftmax(dim=1)
def forward(self, x):
batch_size = x.size(0)
x = get_graph_feature(x, k=self.k)
x = self.conv1(x)
x1 = x.max(dim=-1, keepdim=False)[0]
x = get_graph_feature(x1, k=self.k)
x = self.conv2(x)
x2 = x.max(dim=-1, keepdim=False)[0]
x = get_graph_feature(x2, k=self.k)
x = self.conv3(x)
x3 = x.max(dim=-1, keepdim=False)[0]
x = get_graph_feature(x3, k=self.k)
x = self.conv4(x)
x4 = x.max(dim=-1, keepdim=False)[0]
x = torch.cat((x1, x2, x3, x4), dim=1)
x = self.conv5(x)
x1 = F.adaptive_max_pool1d(x, 1).view(batch_size, -1)
x2 = F.adaptive_avg_pool1d(x, 1).view(batch_size, -1)
x = torch.cat((x1, x2), 1)
x = F.leaky_relu(self.bn6(self.linear1(x)), negative_slope=0.2)
x = self.dp1(x)
x = F.leaky_relu(self.bn7(self.linear2(x)), negative_slope=0.2)
x = self.dp2(x)
x = self.linear3(x)
return self.logsoftmax(x)