pytorch构建多模型实例
pytorch构建双模型
第一部分：构建"se_resnet152","DPN92()"双模型
importnumpyasnp
fromfunctoolsimportpartial
importtorch
fromtorchimportnn
importtorch.nn.functionalasF
fromtorch.optimimportSGD,Adam
fromtorch.autogradimportVariable
fromtorch.utils.dataimportDataset,DataLoader
fromtorch.optim.optimizerimportOptimizer
importtorchvision
fromtorchvisionimportmodels
importpretrainedmodels
frompretrainedmodels.modelsimport*
fromtorchimportnn
fromtorchvisionimporttransformsasT
importrandom
random.seed(2050)
np.random.seed(2050)
torch.manual_seed(2050)
torch.cuda.manual_seed_all(2050)
classFCViewer(nn.Module):
defforward(self,x):
returnx.view(x.size(0),-1)
'''DualPathNetworksinPyTorch.'''
classBottleneck(nn.Module):
def__init__(self,last_planes,in_planes,out_planes,dense_depth,stride,first_layer):
super(Bottleneck,self).__init__()
self.out_planes=out_planes
self.dense_depth=dense_depth
self.conv1=nn.Conv2d(last_planes,in_planes,kernel_size=1,bias=False)
self.bn1=nn.BatchNorm2d(in_planes)
self.conv2=nn.Conv2d(in_planes,in_planes,kernel_size=3,stride=stride,padding=1,groups=32,bias=False)
self.bn2=nn.BatchNorm2d(in_planes)
self.conv3=nn.Conv2d(in_planes,out_planes+dense_depth,kernel_size=1,bias=False)
self.bn3=nn.BatchNorm2d(out_planes+dense_depth)
self.shortcut=nn.Sequential()
iffirst_layer:
self.shortcut=nn.Sequential(
nn.Conv2d(last_planes,out_planes+dense_depth,kernel_size=1,stride=stride,bias=False),
nn.BatchNorm2d(out_planes+dense_depth)
)
defforward(self,x):
out=F.relu(self.bn1(self.conv1(x)))
out=F.relu(self.bn2(self.conv2(out)))
out=self.bn3(self.conv3(out))
x=self.shortcut(x)
d=self.out_planes
out=torch.cat([x[:,:d,:,:]+out[:,:d,:,:],x[:,d:,:,:],out[:,d:,:,:]],1)
out=F.relu(out)
returnout
classDPN(nn.Module):
def__init__(self,cfg):
super(DPN,self).__init__()
in_planes,out_planes=cfg['in_planes'],cfg['out_planes']
num_blocks,dense_depth=cfg['num_blocks'],cfg['dense_depth']
self.conv1=nn.Conv2d(7,64,kernel_size=3,stride=1,padding=1,bias=False)
self.bn1=nn.BatchNorm2d(64)
self.last_planes=64
self.layer1=self._make_layer(in_planes[0],out_planes[0],num_blocks[0],dense_depth[0],stride=1)
self.layer2=self._make_layer(in_planes[1],out_planes[1],num_blocks[1],dense_depth[1],stride=2)
self.layer3=self._make_layer(in_planes[2],out_planes[2],num_blocks[2],dense_depth[2],stride=2)
self.layer4=self._make_layer(in_planes[3],out_planes[3],num_blocks[3],dense_depth[3],stride=2)
self.linear=nn.Linear(out_planes[3]+(num_blocks[3]+1)*dense_depth[3],64)
self.bn2=nn.BatchNorm1d(64)
def_make_layer(self,in_planes,out_planes,num_blocks,dense_depth,stride):
strides=[stride]+[1]*(num_blocks-1)
layers=[]
fori,strideinenumerate(strides):
layers.append(Bottleneck(self.last_planes,in_planes,out_planes,dense_depth,stride,i==0))
self.last_planes=out_planes+(i+2)*dense_depth
returnnn.Sequential(*layers)
defforward(self,x):
out=F.relu(self.bn1(self.conv1(x)))
out=self.layer1(out)
out=self.layer2(out)
out=self.layer3(out)
out=self.layer4(out)
out=F.avg_pool2d(out,4)
out=out.view(out.size(0),-1)
out=self.linear(out)
out=F.relu(self.bn2(out))
returnout
defDPN26():
cfg={
'in_planes':(96,192,384,768),
'out_planes':(256,512,1024,2048),
'num_blocks':(2,2,2,2),
'dense_depth':(16,32,24,128)
}
returnDPN(cfg)
defDPN92():
cfg={
'in_planes':(96,192,384,768),
'out_planes':(256,512,1024,2048),
'num_blocks':(3,4,20,3),
'dense_depth':(16,32,24,128)
}
returnDPN(cfg)
classMultiModalNet(nn.Module):
def__init__(self,backbone1,backbone2,drop,pretrained=True):
super().__init__()
ifpretrained:
img_model=pretrainedmodels.__dict__[backbone1](num_classes=1000,pretrained='imagenet')#seresnext101
else:
img_model=pretrainedmodels.__dict__[backbone1](num_classes=1000,pretrained=None)
self.visit_model=DPN26()
self.img_encoder=list(img_model.children())[:-2]
self.img_encoder.append(nn.AdaptiveAvgPool2d(1))
self.img_encoder=nn.Sequential(*self.img_encoder)
ifdrop>0:
self.img_fc=nn.Sequential(FCViewer(),
nn.Dropout(drop),
nn.Linear(img_model.last_linear.in_features,512),
nn.BatchNorm1d(512))
else:
self.img_fc=nn.Sequential(
FCViewer(),
nn.BatchNorm1d(img_model.last_linear.in_features),
nn.Linear(img_model.last_linear.in_features,512))
self.bn=nn.BatchNorm1d(576)
self.cls=nn.Linear(576,9)
defforward(self,x_img,x_vis):
x_img=self.img_encoder(x_img)
x_img=self.img_fc(x_img)
x_vis=self.visit_model(x_vis)
x_cat=torch.cat((x_img,x_vis),1)
x_cat=F.relu(self.bn(x_cat))
x_cat=self.cls(x_cat)
returnx_cat
test_x=Variable(torch.zeros(64,7,26,24))
test_x1=Variable(torch.zeros(64,3,224,224))
model=MultiModalNet("se_resnet152","DPN92()",0.1)
out=model(test_x1,test_x)
print(model._modules.keys())
print(model)
print(out.shape)
第二部分构建densenet201单模型
#encoding:utf-8
importtorchvision.modelsasmodels
importtorch
importpretrainedmodels
fromtorchimportnn
fromtorch.autogradimportVariable
#model=models.resnet18(pretrained=True)
#print(model)
#print(model._modules.keys())
#feature=torch.nn.Sequential(*list(model.children())[:-2])#模型的结构
#print(feature)
'''
classFCViewer(nn.Module):
defforward(self,x):
returnx.view(x.size(0),-1)
classM(nn.Module):
def__init__(self,backbone1,drop,pretrained=True):
super(M,self).__init__()
ifpretrained:
img_model=pretrainedmodels.__dict__[backbone1](num_classes=1000,pretrained='imagenet')
else:
img_model=pretrainedmodels.__dict__[backbone1](num_classes=1000,pretrained=None)
self.img_encoder=list(img_model.children())[:-1]
self.img_encoder.append(nn.AdaptiveAvgPool2d(1))
self.img_encoder=nn.Sequential(*self.img_encoder)
ifdrop>0:
self.img_fc=nn.Sequential(FCViewer(),
nn.Dropout(drop),
nn.Linear(img_model.last_linear.in_features,236))
else:
self.img_fc=nn.Sequential(
FCViewer(),
nn.Linear(img_model.last_linear.in_features,236)
)
self.cls=nn.Linear(236,9)
defforward(self,x_img):
x_img=self.img_encoder(x_img)
x_img=self.img_fc(x_img)
returnx_img
model1=M('densenet201',0,pretrained=True)
print(model1)
print(model1._modules.keys())
feature=torch.nn.Sequential(*list(model1.children())[:-2])#模型的结构
feature1=torch.nn.Sequential(*list(model1.children())[:])
#print(feature)
#print(feature1)
test_x=Variable(torch.zeros(1,3,100,100))
out=feature(test_x)
print(out.shape)
'''
'''
importtorch.nn.functionalasF
classLenetNet(nn.Module):
def__init__(self):
super(LenetNet,self).__init__()
self.conv1=nn.Conv2d(7,6,5)
self.conv2=nn.Conv2d(6,16,5)
self.fc1=nn.Linear(144,120)
self.fc2=nn.Linear(120,84)
self.fc3=nn.Linear(84,10)
defforward(self,x):
x=F.max_pool2d(F.relu(self.conv1(x)),(2,2))
x=F.max_pool2d(F.relu(self.conv2(x)),2)
x=x.view(x.size()[0],-1)
x=F.relu(self.fc1(x))
x=F.relu(self.fc2(x))
x=self.fc3(x)
returnx
model1=LenetNet()
#print(model1)
#print(model1._modules.keys())
feature=torch.nn.Sequential(*list(model1.children())[:-3])#模型的结构
#feature1=torch.nn.Sequential(*list(model1.children())[:])
print(feature)
#print(feature1)
test_x=Variable(torch.zeros(1,7,27,24))
out=model1(test_x)
print(out.shape)
classFCViewer(nn.Module):
defforward(self,x):
returnx.view(x.size(0),-1)
classM(nn.Module):
def__init__(self):
super(M,self).__init__()
img_model=model1
self.img_encoder=list(img_model.children())[:-3]
self.img_encoder.append(nn.AdaptiveAvgPool2d(1))
self.img_encoder=nn.Sequential(*self.img_encoder)
self.img_fc=nn.Sequential(FCViewer(),
nn.Linear(16,236))
self.cls=nn.Linear(236,9)
defforward(self,x_img):
x_img=self.img_encoder(x_img)
x_img=self.img_fc(x_img)
returnx_img
model2=M()
test_x=Variable(torch.zeros(1,7,27,24))
out=model2(test_x)
print(out.shape)
'''
以上这篇pytorch构建多模型实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持毛票票。
声明：本文内容来源于网络，版权归原作者所有，内容由互联网用户自发贡献自行上传，本网站不拥有所有权，未作人工编辑处理，也不承担相关法律责任。如果您发现有涉嫌版权的内容，欢迎发送邮件至：czq8825#qq.com（发邮件时，请将#更换为@）进行举报，并提供相关证据，一经查实，本站将立刻删除涉嫌侵权内容。