pytorch 训练数据以及测试 全部代码(6) 网络
ResNet101和ASPP
model = ResNet(nInputChannels, Bottleneck, [3, 4, 23, 3], os, pretrained=pretrained)nInputChannels=3，os=16，其中Bottleneck是一个网络：class Bottleneck(nn.Module)先看Bottleneck网络：
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, rate=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
dilation=rate, padding=rate, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True) # 会改变输入的数据，使得输入的数据和输出数据一样
self.downsample = downsample
self.stride = stride
self.rate = rate
def forward(self, x):
residual = 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:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out这是一个bottleneck，输入是x，输出是output+residual。这两个tensor的shape是一样的才能允许相加，如果输入的shape不等于输出的shape那么一定存在downsample，进行shape的变化。所有的卷积都不添加bias，所有的输入经过relu函数之后都改变了数值，使得和输出是一样的。
这里的卷积大小计算重申一下： [n+2p-r(k-1)+1]/s +1
再看resnet101网络，里面有6个函数，下面就一个一个讲解
class ResNet(nn.Module):
def __init__(self, nInputChannels, block, layers, os=16, pretrained=False):
pass
def _make_layer(self, block, planes, blocks, stride=1, rate=1):
pass
def _make_MG_unit(self, block, planes, blocks=[1,2,4], stride=1, rate=1):
pass
def forward(self, input):
pass
def _init_weight(self):
pass
def _load_pretrained_model(self):
pass第一个函数：nInputChannels=3，layers=[3, 4, 23, 3]也就是resnet101的block的层数参照论文https://blog.csdn.net/lanran2/article/details/79057994
def __init__(self, nInputChannels, block, layers, os=16, pretrained=False):
self.inplanes = 64
super(ResNet, self).__init__()
if os == 16:
strides = [1, 2, 2, 1]
rates = [1, 1, 1, 2]
blocks = [1, 2, 4]
elif os == 8:
strides = [1, 2, 1, 1]
rates = [1, 1, 2, 2]
blocks = [1, 2, 1]
else:
raise NotImplementedError
# Modules
self.conv1 = nn.Conv2d(nInputChannels, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0], stride=strides[0], rate=rates[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=strides[1], rate=rates[1])
self.layer3 = self._make_layer(block, 256, layers[2], stride=strides[2], rate=rates[2])
self.layer4 = self._make_MG_unit(block, 512, blocks=blocks, stride=strides[3], rate=rates[3])
self._init_weight()
if pretrained:
self._load_pretrained_model()其中定义maxpool层如下：输出的h，w的计算方式和卷积的计算方式是一样的，通道保持和输入一样。
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)接着：
self.layer1 = self._make_layer(block, 64, layers[0], stride=strides[0], rate=rates[0])函数_make_layer()：block是网络块，planes是特征图的层数就是通道数，blocks是网络块的数目,这里的block.expansion=4
def _make_layer(self, block, planes, blocks, stride=1, rate=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, rate, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)接着：
self.layer4 = self._make_MG_unit(block, 512, blocks=blocks, stride=strides[3], rate=rates[3])函数_make_MG_unit:定义如下：是将不同rate的联合在一起
def _make_MG_unit(self, block, planes, blocks=[1,2,4], stride=1, rate=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, rate=blocks[0]*rate, downsample=downsample))
self.inplanes = planes * block.expansion
for i in range(1, len(blocks)):
layers.append(block(self.inplanes, planes, stride=1, rate=blocks[i]*rate))
return nn.Sequential(*layers)接着是
self._init_weight()定义如下：将模型所有的参数初始化
def _init_weight(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
# n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
# m.weight.data.normal_(0, math.sqrt(2. / n))
torch.nn.init.kaiming_normal_(m.weight)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()接下来
if pretrained:
self._load_pretrained_model()函数_load_pretrained_model定义如下：网络不一定相同，但是相同的参数就进行加载
def _load_pretrained_model(self):
pretrain_dict = model_zoo.load_url('https://download.pytorch.org/models/resnet101-5d3b4d8f.pth')
model_dict = {}
state_dict = self.state_dict()
for k, v in pretrain_dict.items():
if k in state_dict:
model_dict[k] = v
state_dict.update(model_dict)
self.load_state_dict(state_dict)然后看forward函数：
def forward(self, input):
x = self.conv1(input)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
low_level_feat = x
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
return x, low_level_feat
这个是网络层的结构。
下一个讲解ASPP网络