我在改进centernet模型， 准备把resnet50主干网络中的几张特征图额外进行一个特征融合，输出融合后的特征图添加到后面模块里。但主函数里输出的是一个操作序列，不知道该怎么输出这额外的一个变量？
resnet
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
# 512,512,3 -> 256,256,64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
# 256x256x64 -> 128x128x64
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=0, ceil_mode=True) # change
# 128x128x64 -> 128x128x256
self.layer1 = self._make_layer(block, 64, layers[0])
# 128x128x256 -> 64x64x512
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
# 64x64x512 -> 32x32x1024
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
# 32x32x1024 -> 16x16x2048
self.layer4 = self._make_layer(block, 512, layers[3],stride=2)
self.avgpool = nn.AvgPool2d(7)
self.fc = nn.Linear(512 * block.expansion, num_classes)
# 权重初始化
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))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
# 第一个参数表示是bottleneck类，第二个表示该block的输出channel，第三个表示每个block包含多少残差，对应下面的[3, 4, 6, 3]
def _make_layer(self, block, planes, blocks,stride=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, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.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) # 128x128x64 -> 128x128x256
x = self.layer2(x) # 128x128x256 -> 64x64x512
x = self.layer3(x) # 64x64x512 -> 32x32x1024
x = self.layer4(x)# 32x32x1024 -> 16x16x2048
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
主函数
def resnet50(pretrained = True):
model = ResNet(Bottleneck, [3, 4, 6, 3])#第一个参数用的是bottleneck，第二个参数是每层里卷积数量
if pretrained:
state_dict = load_state_dict_from_url(model_urls['resnet50'], model_dir = 'model_data/')#导入预训练参数
model.load_state_dict(state_dict)#用预训练的模型参数来初始化你构建的网络结构
#----------------------------------------------------------#
# 获取特征提取部分
#----------------------------------------------------------#
features = list([model.conv1, model.bn1, model.relu, model.maxpool, model.layer1, model.layer2, model.layer3, model.layer4])
features = nn.Sequential(*features)
return features #输出一个操作序列
centernet模型里各模块顺序
class CenterNet_Resnet50(nn.Module):
def __init__(self, num_classes = 20, pretrained = False):
super(CenterNet_Resnet50, self).__init__()
#预训练 主干网络提取特征→解码→检测头
self.pretrained = pretrained
# 512,512,3 -> 16,16,2048
self.backbone = resnet50(pretrained = pretrained)
# 16,16,2048 -> 128,128,64
self.decoder = resnet50_Decoder(2048)
#-----------------------------------------------------------------#
# 对获取到的特征进行上采样，进行分类预测和回归预测
# 128, 128, 64 -> 128, 128, 64 -> 128, 128, num_classes
# -> 128, 128, 64 -> 128, 128, 2
# -> 128, 128, 64 -> 128, 128, 2
#-----------------------------------------------------------------#
self.head = resnet50_Head(channel=64, num_classes=num_classes)
self._init_weights()
def freeze_backbone(self):
for param in self.backbone.parameters():
param.requires_grad = False
def unfreeze_backbone(self):
for param in self.backbone.parameters():
param.requires_grad = True
def _init_weights(self):
if not self.pretrained:
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))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
self.head.cls_head[-1].weight.data.fill_(0)
self.head.cls_head[-1].bias.data.fill_(-2.19)
def forward(self, x):
feat = self.backbone(x)
feat=self.decoder(feat)
return self.head(feat)
