File size: 5,913 Bytes
1173b78 |
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 |
import torch.nn as nn
from torch.nn import (
Linear,
Conv2d,
BatchNorm1d,
BatchNorm2d,
ReLU,
Dropout,
MaxPool2d,
Sequential,
Module,
)
# Support: ['ResNet_50', 'ResNet_101', 'ResNet_152']
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return Conv2d(
in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False
)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = BatchNorm2d(planes)
self.relu = ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = BatchNorm2d(planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = BatchNorm2d(planes * self.expansion)
self.relu = ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(Module):
def __init__(self, input_size, block, layers, zero_init_residual=True):
super(ResNet, self).__init__()
assert input_size[0] in [
112,
224,
], "input_size should be [112, 112] or [224, 224]"
self.inplanes = 64
self.conv1 = Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.bn1 = BatchNorm2d(64)
self.relu = ReLU(inplace=True)
self.maxpool = MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.bn_o1 = BatchNorm2d(2048)
self.dropout = Dropout()
if input_size[0] == 112:
self.fc = Linear(2048 * 4 * 4, 512)
else:
self.fc = Linear(2048 * 8 * 8, 512)
self.bn_o2 = BatchNorm1d(512)
for m in self.modules():
if isinstance(m, Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
elif isinstance(m, BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.bn_o1(x)
x = self.dropout(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
x = self.bn_o2(x)
return x
def ResNet_18(input_size, **kwargs):
"""Constructs a ResNet-50 model."""
model = ResNet(input_size, Bottleneck, [2, 2, 2, 2], **kwargs)
return model
def ResNet_50(input_size, **kwargs):
"""Constructs a ResNet-50 model."""
model = ResNet(input_size, Bottleneck, [3, 4, 6, 3], **kwargs)
return model
def ResNet_101(input_size, **kwargs):
"""Constructs a ResNet-101 model."""
model = ResNet(input_size, Bottleneck, [3, 4, 23, 3], **kwargs)
return model
def ResNet_152(input_size, **kwargs):
"""Constructs a ResNet-152 model."""
model = ResNet(input_size, Bottleneck, [3, 8, 36, 3], **kwargs)
return model
|