深度可分离U

2024-07-11 04:03| 来源: 网络整理| 查看: 265

1、背景

U_Net自提出之后就被各种操作，原因是结构简单，易改造，因此我受到Mobilenet的启发，也决定来改改玩。在提出的结构中将原来的通用卷积替换为深度可分离卷积，同时在分离卷积中又使用了扩张卷积，同时也利用了残差结构。

2、结构优势

2.1 深度可分离卷积：将空间特征和通道特征分开提取，极大的减少了运算的参数量。

2.2 扩张卷积：可以获得不同的感受野信息，对语义分割十分有利。

2.3 残差结构：能够使特征更快的向前传播易及残差函数更易优化，避免过拟合等。

3、代码

原模型结构：

import torch from torch import nn class block_down(nn.Module): def __init__(self,inp_channel,out_channel): super(block_down,self).__init__() self.conv1=nn.Conv2d(inp_channel,out_channel,3,padding=1) self.conv2=nn.Conv2d(out_channel,out_channel,3,padding=1) self.bn=nn.BatchNorm2d(out_channel) self.relu=nn.ReLU6(inplace=True) def forward(self,x): x=self.conv1(x) x=self.bn(x) x=self.relu(x) x=self.conv2(x) x=self.bn(x) x=self.relu(x) return x class block_up(nn.Module): def __init__(self,inp_channel,out_channel): super(block_up,self).__init__() self.up=nn.ConvTranspose2d(inp_channel,out_channel,2,stride=2) self.conv1=nn.Conv2d(inp_channel,out_channel,3,padding=1) self.conv2=nn.Conv2d(out_channel,out_channel,3,padding=1) self.bn=nn.BatchNorm2d(out_channel) self.relu=nn.ReLU6(inplace=True) def forward(self,x,y): x=self.up(x) x=torch.cat([x,y],dim=1) x=self.conv1(x) x=self.bn(x) x=self.relu(x) x=self.conv2(x) x=self.bn(x) x=self.relu(x) return x class U_net(nn.Module): def __init__(self,out_channel): super(U_net,self).__init__() self.out=nn.Conv2d(64,out_channel,1) self.maxpool=nn.MaxPool2d(2) self.block_down=block_down self.block_up=block_up self.block1=block_down(3,64) self.block2=block_down(64,128) self.block3=block_down(128,256) self.block4=block_down(256,512) self.block5=block_down(512,1024) self.block6=block_up(1024,512) self.block7=block_up(512,256) self.block8=block_up(256,128) self.block9=block_up(128,64) def forward(self,x): x1_use=self.block1(x) x1=self.maxpool(x1_use) x2_use=self.block2(x1) x2=self.maxpool(x2_use) x3_use=self.block3(x2) x3=self.maxpool(x3_use) x4_use=self.block4(x3) x4=self.maxpool(x4_use) x5=self.block5(x4) x6=self.block6(x5,x4_use) x7=self.block7(x6,x3_use) x8=self.block8(x7,x2_use) x9=self.block9(x8,x1_use) out=self.out(x9) return out if __name__ == "__main__": test_input = torch.rand(1, 3, 480, 640).to("cuda") print("input_size:", test_input.size()) model = U_net(3) model.cuda() ouput = model(test_input) print("output_size:", ouput.size()) params = list(model.named_parameters()) k = 0 for name, param in params: print(name) if param.requires_grad: l = 1 for i in param.size(): l *= i k = k + l print(l) print("模型总的参数量是：" + str(k))

原模型运算结果为：

input_size: torch.Size([1, 3, 480, 640]) output_size: torch.Size([1, 3, 480, 640]) out.weight 192 out.bias 3 block1.conv1.weight 1728 block1.conv1.bias 64 block1.conv2.weight 36864 block1.conv2.bias 64 block1.bn.weight 64 block1.bn.bias 64 block2.conv1.weight 73728 block2.conv1.bias 128 block2.conv2.weight 147456 block2.conv2.bias 128 block2.bn.weight 128 block2.bn.bias 128 block3.conv1.weight 294912 block3.conv1.bias 256 block3.conv2.weight 589824 block3.conv2.bias 256 block3.bn.weight 256 block3.bn.bias 256 block4.conv1.weight 1179648 block4.conv1.bias 512 block4.conv2.weight 2359296 block4.conv2.bias 512 block4.bn.weight 512 block4.bn.bias 512 block5.conv1.weight 4718592 block5.conv1.bias 1024 block5.conv2.weight 9437184 block5.conv2.bias 1024 block5.bn.weight 1024 block5.bn.bias 1024 block6.up.weight 2097152 block6.up.bias 512 block6.conv1.weight 4718592 block6.conv1.bias 512 block6.conv2.weight 2359296 block6.conv2.bias 512 block6.bn.weight 512 block6.bn.bias 512 block7.up.weight 524288 block7.up.bias 256 block7.conv1.weight 1179648 block7.conv1.bias 256 block7.conv2.weight 589824 block7.conv2.bias 256 block7.bn.weight 256 block7.bn.bias 256 block8.up.weight 131072 block8.up.bias 128 block8.conv1.weight 294912 block8.conv1.bias 128 block8.conv2.weight 147456 block8.conv2.bias 128 block8.bn.weight 128 block8.bn.bias 128 block9.up.weight 32768 block9.up.bias 64 block9.conv1.weight 73728 block9.conv1.bias 64 block9.conv2.weight 36864 block9.conv2.bias 64 block9.bn.weight 64 block9.bn.bias 64 模型总的参数量是：31037763

新模型结构：

import torch from torch import nn import torch.nn.functional as F def fixed_padding(inputs, kernel_size, dilation): kernel_size_effective = kernel_size + (kernel_size - 1) * (dilation - 1) pad_total = kernel_size_effective - 1 pad_beg = pad_total // 2 pad_end = pad_total - pad_beg padded_inputs = F.pad(inputs, (pad_beg, pad_end, pad_beg, pad_end)) return padded_inputs class InvertedResidual(nn.Module): def __init__(self, inp, oup, expand): super(InvertedResidual, self).__init__() self.expand=expand self.conv = nn.Sequential( # dw nn.Conv2d(inp, inp, 3, 1, 0, dilation=expand, groups=inp, bias=False), nn.BatchNorm2d(inp), nn.ReLU6(inplace=True), # pw nn.Conv2d(inp, oup, 1, 1, 0, 1, bias=False), ) def forward(self, x): x_pad = fixed_padding(x, 3, self.expand) y= self.conv(x_pad) return y class block_down(nn.Module): def __init__(self, inp_channel, out_channel, expand): super(block_down, self).__init__() self.deepwise1 = InvertedResidual(inp_channel, inp_channel, expand) self.deepwise2 = InvertedResidual(inp_channel, out_channel, expand) self.resnet= nn.Conv2d(inp_channel, out_channel, 1, 1, 0, 1, bias=False) def forward(self, input): resnet=self.resnet(input) x = self.deepwise1(input) x= self.deepwise2(x) out=torch.add(resnet,x) return out class block_up(nn.Module): def __init__(self, inp_channel, out_channel, expand): super(block_up, self).__init__() self.up = nn.ConvTranspose2d(inp_channel, out_channel, 2, stride=2) self.deepwise1 = InvertedResidual(inp_channel, inp_channel, expand) self.deepwise2 = InvertedResidual(inp_channel, out_channel, expand) self.resnet = nn.Conv2d(inp_channel, out_channel, 1, 1, 0, 1, bias=False) def forward(self, x, y): x = self.up(x) x1 = torch.cat([x, y], dim=1) x = self.deepwise1(x1) x = self.deepwise2(x) resnet=self.resnet(x1) out=torch.add(resnet,x) return out class U_net(nn.Module): def __init__(self, class_num): super(U_net, self).__init__() self.inp = nn.Conv2d(3, 64, 1) self.block2 = block_down(64, 128, expand=1) self.block3 = block_down(128, 256, expand=2) self.block4 = block_down(256, 512, expand=2) self.block5 = block_down(512, 1024, expand=1) self.block6 = block_up(1024, 512, expand=1) self.block7 = block_up(512, 256, expand=1) self.block8 = block_up(256, 128, expand=2) self.block9 = block_up(128, 64, expand=2) self.out = nn.Conv2d(64, class_num, 1) self.maxpool = nn.MaxPool2d(2) def forward(self, x): x1_use = self.inp(x) x1 = self.maxpool(x1_use) x2_use = self.block2(x1) x2 = self.maxpool(x2_use) x3_use = self.block3(x2) x3 = self.maxpool(x3_use) x4_use = self.block4(x3) x4 = self.maxpool(x4_use) x5 = self.block5(x4) x6 = self.block6(x5, x4_use) x7 = self.block7(x6, x3_use) x8 = self.block8(x7, x2_use) x9 = self.block9(x8, x1_use) out= self.out(x9) return out if __name__ == "__main__": test_input = torch.rand(1, 3, 480, 640).to("cuda") print("input_size:", test_input.size()) model = U_net(3) model.cuda() ouput = model(test_input) print("output_size:", ouput.size()) params=list(model.named_parameters()) k=0 for name,param in params: print(name) if param.requires_grad: l=1 for i in param.size(): l*=i k=k+l print(l) print("模型总的参数量是："+str(k))

4、新模型运行结果

input_size: torch.Size([1, 3, 480, 640]) output_size: torch.Size([1, 3, 480, 640]) inp.weight 192 inp.bias 64 block2.deepwise1.conv.0.weight 576 block2.deepwise1.conv.1.weight 64 block2.deepwise1.conv.1.bias 64 block2.deepwise1.conv.3.weight 4096 block2.deepwise2.conv.0.weight 576 block2.deepwise2.conv.1.weight 64 block2.deepwise2.conv.1.bias 64 block2.deepwise2.conv.3.weight 8192 block2.resnet.weight 8192 block3.deepwise1.conv.0.weight 1152 block3.deepwise1.conv.1.weight 128 block3.deepwise1.conv.1.bias 128 block3.deepwise1.conv.3.weight 16384 block3.deepwise2.conv.0.weight 1152 block3.deepwise2.conv.1.weight 128 block3.deepwise2.conv.1.bias 128 block3.deepwise2.conv.3.weight 32768 block3.resnet.weight 32768 block4.deepwise1.conv.0.weight 2304 block4.deepwise1.conv.1.weight 256 block4.deepwise1.conv.1.bias 256 block4.deepwise1.conv.3.weight 65536 block4.deepwise2.conv.0.weight 2304 block4.deepwise2.conv.1.weight 256 block4.deepwise2.conv.1.bias 256 block4.deepwise2.conv.3.weight 131072 block4.resnet.weight 131072 block5.deepwise1.conv.0.weight 4608 block5.deepwise1.conv.1.weight 512 block5.deepwise1.conv.1.bias 512 block5.deepwise1.conv.3.weight 262144 block5.deepwise2.conv.0.weight 4608 block5.deepwise2.conv.1.weight 512 block5.deepwise2.conv.1.bias 512 block5.deepwise2.conv.3.weight 524288 block5.resnet.weight 524288 block6.up.weight 2097152 block6.up.bias 512 block6.deepwise1.conv.0.weight 9216 block6.deepwise1.conv.1.weight 1024 block6.deepwise1.conv.1.bias 1024 block6.deepwise1.conv.3.weight 1048576 block6.deepwise2.conv.0.weight 9216 block6.deepwise2.conv.1.weight 1024 block6.deepwise2.conv.1.bias 1024 block6.deepwise2.conv.3.weight 524288 block6.resnet.weight 524288 block7.up.weight 524288 block7.up.bias 256 block7.deepwise1.conv.0.weight 4608 block7.deepwise1.conv.1.weight 512 block7.deepwise1.conv.1.bias 512 block7.deepwise1.conv.3.weight 262144 block7.deepwise2.conv.0.weight 4608 block7.deepwise2.conv.1.weight 512 block7.deepwise2.conv.1.bias 512 block7.deepwise2.conv.3.weight 131072 block7.resnet.weight 131072 block8.up.weight 131072 block8.up.bias 128 block8.deepwise1.conv.0.weight 2304 block8.deepwise1.conv.1.weight 256 block8.deepwise1.conv.1.bias 256 block8.deepwise1.conv.3.weight 65536 block8.deepwise2.conv.0.weight 2304 block8.deepwise2.conv.1.weight 256 block8.deepwise2.conv.1.bias 256 block8.deepwise2.conv.3.weight 32768 block8.resnet.weight 32768 block9.up.weight 32768 block9.up.bias 64 block9.deepwise1.conv.0.weight 1152 block9.deepwise1.conv.1.weight 128 block9.deepwise1.conv.1.bias 128 block9.deepwise1.conv.3.weight 16384 block9.deepwise2.conv.0.weight 1152 block9.deepwise2.conv.1.weight 128 block9.deepwise2.conv.1.bias 128 block9.deepwise2.conv.3.weight 8192 block9.resnet.weight 8192 out.weight 192 out.bias 3 模型总的参数量是：7376131

可以看出参数量减少了3/4，新模型在我自己的数据集上语义分割任务中运行到第一个epoch时候的miou已经达到了0.5465。而原始U_Net的第一个epoch的miou为0.2590，当然这也不足以说明什么，但是新模型的batch size要设的比较小一点，比较耗显存，原因不明。新模型的检测速度为8.65ms（1080ti，单图480×640）。旧模型的检测速度为6.64ms，原因不明。

5、总结

模型明显参数减少，精度有“可能”提高了，速度却降下去了，模型有待后面继续测验。

【本文地址】

公司简介

联系我们