File size: 8,311 Bytes
caa56d6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
import torch
import torch.nn as nn
import torch.nn.functional as F
import os
import sys
class SeparableConv2d(nn.Module):
def __init__(self, c_in, c_out, ks, stride=1, padding=0, dilation=1, bias=False):
super(SeparableConv2d, self).__init__()
self.c = nn.Conv2d(c_in, c_in, ks, stride, padding, dilation, groups=c_in, bias=bias)
self.pointwise = nn.Conv2d(c_in, c_out, 1, 1, 0, 1, 1, bias=bias)
def forward(self, x):
x = self.c(x)
x = self.pointwise(x)
return x
class Block(nn.Module):
def __init__(self, c_in, c_out, reps, stride=1, start_with_relu=True, grow_first=True):
super(Block, self).__init__()
self.skip = None
self.skip_bn = None
if c_out != c_in or stride!= 1:
self.skip = nn.Conv2d(c_in, c_out, 1, stride=stride, bias=False)
self.skip_bn = nn.BatchNorm2d(c_out)
self.relu = nn.ReLU(inplace=True)
rep = []
c = c_in
if grow_first:
rep.append(self.relu)
rep.append(SeparableConv2d(c_in, c_out, 3, stride=1, padding=1, bias=False))
rep.append(nn.BatchNorm2d(c_out))
c = c_out
for i in range(reps - 1):
rep.append(self.relu)
rep.append(SeparableConv2d(c, c, 3, stride=1, padding=1, bias=False))
rep.append(nn.BatchNorm2d(c))
if not grow_first:
rep.append(self.relu)
rep.append(SeparableConv2d(c_in, c_out, 3, stride=1, padding=1, bias=False))
rep.append(nn.BatchNorm2d(c_out))
if not start_with_relu:
rep = rep[1:]
else:
rep[0] = nn.ReLU(inplace=False)
if stride != 1:
rep.append(nn.MaxPool2d(3, stride, 1))
self.rep = nn.Sequential(*rep)
def forward(self, inp):
x = self.rep(inp)
if self.skip is not None:
y = self.skip(inp)
y = self.skip_bn(y)
else:
y = inp
x += y
return x
class RegressionMap(nn.Module):
def __init__(self, c_in):
super(RegressionMap, self).__init__()
self.c = SeparableConv2d(c_in, 1, 3, stride=1, padding=1, bias=False)
self.s = nn.Sigmoid()
def forward(self, x):
mask = self.c(x)
mask = self.s(mask)
return mask, None
class TemplateMap(nn.Module):
def __init__(self, c_in, templates):
super(TemplateMap, self).__init__()
self.c = Block(c_in, 364, 2, 2, start_with_relu=True, grow_first=False)
self.l = nn.Linear(364, 10)
self.relu = nn.ReLU(inplace=True)
self.templates = templates
def forward(self, x):
v = self.c(x)
v = self.relu(v)
v = F.adaptive_avg_pool2d(v, (1,1))
v = v.view(v.size(0), -1)
v = self.l(v)
mask = torch.mm(v, self.templates.reshape(10,361))
mask = mask.reshape(x.shape[0], 1, 19, 19)
return mask, v
class PCATemplateMap(nn.Module):
def __init__(self, templates):
super(PCATemplateMap, self).__init__()
self.templates = templates
def forward(self, x):
fe = x.view(x.shape[0], x.shape[1], x.shape[2]*x.shape[3])
fe = torch.transpose(fe, 1, 2)
mu = torch.mean(fe, 2, keepdim=True)
fea_diff = fe - mu
cov_fea = torch.bmm(fea_diff, torch.transpose(fea_diff, 1, 2))
B = self.templates.reshape(1, 10, 361).repeat(x.shape[0], 1, 1)
D = torch.bmm(torch.bmm(B, cov_fea), torch.transpose(B, 1, 2))
eigen_value, eigen_vector = D.symeig(eigenvectors=True)
index = torch.tensor([9]).cuda()
eigen = torch.index_select(eigen_vector, 2, index)
v = eigen.squeeze(-1)
mask = torch.mm(v, self.templates.reshape(10, 361))
mask = mask.reshape(x.shape[0], 1, 19, 19)
return mask, v
class Xception(nn.Module):
"""
Xception optimized for the ImageNet dataset, as specified in
https://arxiv.org/pdf/1610.02357.pdf
"""
def __init__(self, maptype, templates, num_classes=1000):
super(Xception, self).__init__()
self.num_classes = num_classes
self.conv1 = nn.Conv2d(3, 32, 3,2, 0, bias=False)
self.bn1 = nn.BatchNorm2d(32)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(32,64,3,bias=False)
self.bn2 = nn.BatchNorm2d(64)
self.block1=Block(64,128,2,2,start_with_relu=False,grow_first=True)
self.block2=Block(128,256,2,2,start_with_relu=True,grow_first=True)
self.block3=Block(256,728,2,2,start_with_relu=True,grow_first=True)
self.block4=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block5=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block6=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block7=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block8=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block9=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block10=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block11=Block(728,728,3,1,start_with_relu=True,grow_first=True)
self.block12=Block(728,1024,2,2,start_with_relu=True,grow_first=False)
self.conv3 = SeparableConv2d(1024,1536,3,1,1)
self.bn3 = nn.BatchNorm2d(1536)
self.conv4 = SeparableConv2d(1536,2048,3,1,1)
self.bn4 = nn.BatchNorm2d(2048)
self.last_linear = nn.Linear(2048, num_classes)
if maptype == 'none':
self.map = [1, None]
elif maptype == 'reg':
self.map = RegressionMap(728)
elif maptype == 'tmp':
self.map = TemplateMap(728, templates)
elif maptype == 'pca_tmp':
self.map = PCATemplateMap(728)
else:
print('Unknown map type: `{0}`'.format(maptype))
sys.exit()
def features(self, input):
x = self.conv1(input)
x = self.bn1(x)
x = self.relu(x)
x = self.conv2(x)
x = self.bn2(x)
x = self.relu(x)
x = self.block1(x)
x = self.block2(x)
x = self.block3(x)
x = self.block4(x)
x = self.block5(x)
x = self.block6(x)
x = self.block7(x)
mask, vec = self.map(x)
x = x * mask
x = self.block8(x)
x = self.block9(x)
x = self.block10(x)
x = self.block11(x)
x = self.block12(x)
x = self.conv3(x)
x = self.bn3(x)
x = self.relu(x)
x = self.conv4(x)
x = self.bn4(x)
return x, mask, vec
def logits(self, features):
x = self.relu(features)
x = F.adaptive_avg_pool2d(x, (1, 1))
x = x.view(x.size(0), -1)
x = self.last_linear(x)
return x
def forward(self, input):
x, mask, vec = self.features(input)
x = self.logits(x)
return x, mask, vec
def init_weights(m):
classname = m.__class__.__name__
if classname.find('SeparableConv2d') != -1:
m.c.weight.data.normal_(0.0, 0.01)
if m.c.bias is not None:
m.c.bias.data.fill_(0)
m.pointwise.weight.data.normal_(0.0, 0.01)
if m.pointwise.bias is not None:
m.pointwise.bias.data.fill_(0)
elif classname.find('Conv') != -1 or classname.find('Linear') != -1:
m.weight.data.normal_(0.0, 0.01)
if m.bias is not None:
m.bias.data.fill_(0)
elif classname.find('BatchNorm') != -1:
m.weight.data.normal_(1.0, 0.01)
m.bias.data.fill_(0)
elif classname.find('LSTM') != -1:
for i in m._parameters:
if i.__class__.__name__.find('weight') != -1:
i.data.normal_(0.0, 0.01)
elif i.__class__.__name__.find('bias') != -1:
i.bias.data.fill_(0)
class Model:
def __init__(self, maptype='None', templates=None, num_classes=2, load_pretrain=True):
model = Xception(maptype, templates, num_classes=num_classes)
if load_pretrain:
state_dict = torch.load('./xception-b5690688.pth')
for name, weights in state_dict:
if 'pointwise' in name:
state_dict[name] = weights.unsqueeze(-1).unsqueeze(-1)
del state_dict['fc.weight']
del state_dict['fc.bias']
model.load_state_dict(state_dict, False)
else:
model.apply(init_weights)
self.model = model
def save(self, epoch, optim, model_dir):
state = {'net': self.model.state_dict(), 'optim': optim.state_dict()}
torch.save(state, '{0}/{1:06d}.tar'.format(model_dir, epoch))
print('Saved model `{0}`'.format(epoch))
def load(self, epoch, model_dir):
filename = '{0}{1:06d}.tar'.format(model_dir, epoch)
print('Loading model from {0}'.format(filename))
if os.path.exists(filename):
state = torch.load(filename)
self.model.load_state_dict(state['net'])
else:
print('Failed to load model from {0}'.format(filename))
|