resnet50是何凯明提出的能够有效解决深网络退化问题的结构之一，它将输入的多重非线性变化拟合变为输入和输出拟合的残差，变为恒等映射，50即50阶
巨神崇拜： https://github.com/KaimingHe
2 .基础框架将block分为两类，block1适用于resnet34以下。 只有双层结构。 应该注意的是，至少应该保证两层，在只有一层的情况下，即
out=f(x，w i ) x=wIxbxout=f ) x，w_i ) x=w_ix b x out=F(x ) x，w i ) x=wi x b x仍然是线性关系
block2结构为三层，加入了一个缩放操作。 具体结构如图所示
跨层次链接时，往往存在维，存在大小不一致的现象。 此时，通常有两种方法。 一个是补零的方法，另一个是用1x1的卷积核缩放，然后应用表达式就可以了
输出=[支持输入核的边长2padIngstrIde (步长) 1输出=(FRAC )输入-支持比对的边长2*padding )=[=[stride步长] 1输出=[stride支持输入比对的边长
通常，深度的倍数和大小的缩小倍数一致
3 .构想代码根据框架编写了代码，但没有经过测试，所以不保证代码完全没有错误~~http://www.Sina.com/
class Conv_b
lock(nn.Module): def __init__(self,in_channels,require_channels): super().__init__() if in_channels!=require_channels: self.downscale=require_channels/in_channels self.residual=nn.Sequential( nn.Conv2d(in_channels,require_channels,kernel_size=1,stride=self.downscale), nn.BatchNorm2d(require_channels), nn.ReLU(), nn.Conv2d(require_channels,require_channels,kernel_size=3), nn.BatchNorm2d(require_channels), nn.ReLU(), nn.Conv2d(require_channels,require_channels*4,kernel_size=3), nn.BatchNorm2d(require_channels*4), nn.ReLU(), ) if self.downscale==4: self.cut=nn.Sequential() else: self.cut=nn.Sequential(nn.Conv2d(in_channels,require_channels*4,kernel_size=1,stride=self.downscale)) def forward(self,x): return nn.ReLU(self.residual(x)+self.cut(x))resnet50:
class Resnet(nn.Module): def __init(self,num_classes): super().__init__() self.downscale=1 self.con1=nn.Sequential( nn.Conv2d(3,64,kernel_size=7,stride=2), nn.MaxPool2d(64,64,kernel_size=3,stride=2), nn.BatchNorm2d(64), nn.ReLU(), ) self.layer1=self._layers(64,64,3) self.layer2=self._layers(64*4,128,4) self.layer3=self._layers(128*4,256,6) self.layer4=self._layers(256*4,512,3) self.classifier=nn.Sequential( nn.AdaptiveAvgPool2d(num_classes*4), nn.AdaptiveAvgPool2d(num_classes), nn.Softmax() ) def _layers(self,in_channels,require_channels,num_blocks): layers=[] for i in range(num_blocks): layers.append(Conv_block(in_channels,require_channels)) in_channels=require_channels*4 return nn.Sequential(*layers) def forward(self,x): con1=self.con1(x) l1=self.layer1(con1) l2=self.layer2(l1) l3=self.layer3(l2) l4=self.layer4(l3) y=self.classifier(l4) return y如果希望自己训练的话，也可以写个训练模块试试
def optim(self,type,lr): param=self.parameters() if type=='Adam': self.optimizer=torch.optim.Adam(param,lr) def define_loss(self,type): if type=='CrossEntropyLoss': self.loss=nn.CrossEntropyLoss() #封装成tensordataset def train(self,train_loader,epochs,gpu=False,optim,lr,loss): self.optim(optim,lr) self.define_loss(loss) batches=len(train_loader) for epoch in range(1,epochs+1): for batch,(data,target) in enumerate(train_loader): lr_rate=lr*(1-epoch/epochs)*(batch/batches) for params in self.optimizer.param_groups: params['lr']=lr_rate if gpu==True: data,target=data.cuda(),target.cuda() out=self.forward(data) total_loss=self.loss(out,target) self.optimizer.zero_grad() total_loss.backward() self.optimizer.step() #每十个batch，打印一次epoch，batch，loss，lr if batch%10==0: print('Epoch:{}/{},batch:{},loss:{},lr:{}' .format(epoch,epochs,batch,total_loss,lr_rate))