VGG-Unet
import torch
import torch.nn as nn
# 定义一个通用的卷积块
class ConvBNReLU(nn.Sequential):
def __init__(self, in_channels, out_channels, kernel_size=3, padding=1):
super(ConvBNReLU, self).__init__(
nn.Conv2d(in_channels, out_channels, kernel_size, padding=padding),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),)
# 使用ConvBNReLU来定义VGGBlock2
class VGGBlock2(nn.Sequential):
def __init__(self, in_channels, middle_channels, out_channels):
super(VGGBlock2, self).__init__(
ConvBNReLU(in_channels, middle_channels),
ConvBNReLU(middle_channels, out_channels),)
class VGGBlock3(nn.Sequential):
def __init__(self, in_channels, middle_channels, out_channels):
super(VGGBlock3, self).__init__(
ConvBNReLU(in_channels, middle_channels),
ConvBNReLU(middle_channels, middle_channels),
ConvBNReLU(middle_channels, out_channels))
class Unet(nn.Module):
def __init__(self, num_classes, input_channels=3, **kwargs):
super().__init__()
#nb_filter = [16, 32, 64, 128,256] #Total params:1,965,586
#nb_filter = [32, 64, 128, 256, 512] #Total params: 7,852,578 Params size (MB): 29.96
nb_filter = [64, 128, 256, 512, 512] # Total params:19,591,234 Params size (MB): 74.73
self.pool = nn.MaxPool2d(2, 2)
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)#scale_factor:放大的倍数 插值
self.conv0_0 = VGGBlock2(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock2(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock3(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock3(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock3(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv3_1 = VGGBlock2(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3])
self.conv2_2 = VGGBlock2(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv1_3 = VGGBlock2(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock2(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0])
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
def forward(self, input):
x0_0 = self.conv0_0(input)
x1_0 = self.conv1_0(self.pool(x0_0))
x2_0 = self.conv2_0(self.pool(x1_0))
x3_0 = self.conv3_0(self.pool(x2_0))
x4_0 = self.conv4_0(self.pool(x3_0))
x3_1 = self.conv3_1(torch.cat([x3_0, self.up(x4_0)], 1))
x2_2 = self.conv2_2(torch.cat([x2_0, self.up(x3_1)], 1))
x1_3 = self.conv1_3(torch.cat([x1_0, self.up(x2_2)], 1))
x0_4 = self.conv0_4(torch.cat([x0_0, self.up(x1_3)], 1))
output = self.final(x0_4)
return output
if __name__ == '__main__':
#u=NestedUNet(2)
#input=torch.randn((1,3,512,512))
#a=u(input)
import torch
from torchsummary import summary
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using {device} device")
model = Unet(2).to(device)
# 创建一个在GPU上的示例输入张量
example_input_size = (3, 512, 512) # 这是一个元组，代表输入张量的尺寸
summary(model, example_input_size)
Unet++
import torch
from torch import nn
# 基本计算单元
class VGGBlock(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels):
super().__init__()
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Conv2d(in_channels, middle_channels, 3, padding=1)
self.bn1 = nn.BatchNorm2d(middle_channels)
self.conv2 = nn.Conv2d(middle_channels, out_channels, 3, padding=1)
self.bn2 = nn.BatchNorm2d(out_channels)
def forward(self, x):
# VGGBlock实际上就是相当于做了两次卷积
out = self.conv1(x)
out = self.bn1(out) # 归一化
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
return out
class Unet(nn.Module):
def __init__(self, num_classes, input_channels=3, deep_supervision=False, **kwargs):
super().__init__()
# 定义了一个列表，包含NestedUNet中不同层的通道数
#nb_filter = [16, 32, 64, 128,256]
nb_filter = [32, 64, 128, 256, 512] #Total params: 7,852,578 Params size (MB): 34.96
#nb_filter = [64, 128, 256, 512, 512]
# 深度监督：是否需要都计算损失函数
self.deep_supervision = deep_supervision
self.pool = nn.MaxPool2d(2, 2) # 最大池化，池化核大小为2x2，步幅为2
# 创建一个上采样层实例，尺度因子为2，采用双线性插值的方式进行上采样，边缘对齐方式为True
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv0_1 = VGGBlock(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_1 = VGGBlock(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_1 = VGGBlock(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv3_1 = VGGBlock(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3])
self.conv0_2 = VGGBlock(nb_filter[0]*2+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_2 = VGGBlock(nb_filter[1]*2+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_2 = VGGBlock(nb_filter[2]*2+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv0_3 = VGGBlock(nb_filter[0]*3+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_3 = VGGBlock(nb_filter[1]*3+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock(nb_filter[0]*4+nb_filter[1], nb_filter[0], nb_filter[0])
if self.deep_supervision:
self.final1 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final2 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final3 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final4 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
else:
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
def forward(self, input):
# 入口函数打个断点，看数据的维度很重要
#print('input:', input.shape)
x0_0 = self.conv0_0(input) # 第一次卷积
#print('x0_0:',x0_0.shape) # 升维 input: torch.Size([8, 32, 96, 96])
x1_0 = self.conv1_0(self.pool(x0_0))
#print('x1_0:', x1_0.shape) # 升维，降数据量，x1_0: torch.Size([8, 32, 96, 96])
x0_1 = self.conv0_1(torch.cat([x0_0, self.up(x1_0)], 1))
# cat 拼接，再经历一次卷积，input是96=32+64，output=32
#print('x0_1:', x0_1.shape) # x0_1: torch.Size([8, 32, 96, 96])
# 梳理清楚一个关键点即可，后面依次类推，可以打印结果自己手动推一下
x2_0 = self.conv2_0(self.pool(x1_0))
# print('x2_0:', x2_0.shape)
x1_1 = self.conv1_1(torch.cat([x1_0, self.up(x2_0)], 1))
#print('x1_1:',x1_1.shape)
x0_2 = self.conv0_2(torch.cat([x0_0, x0_1, self.up(x1_1)], 1))
#print('x0_2:',x0_2.shape)
x3_0 = self.conv3_0(self.pool(x2_0))
#print('x3_0:',x3_0.shape)
x2_1 = self.conv2_1(torch.cat([x2_0, self.up(x3_0)], 1))
#print('x2_1:',x2_1.shape)
x1_2 = self.conv1_2(torch.cat([x1_0, x1_1, self.up(x2_1)], 1))
#print('x1_2:',x1_2.shape)
x0_3 = self.conv0_3(torch.cat([x0_0, x0_1, x0_2, self.up(x1_2)], 1))
# print('x0_3:',x0_3.shape)
x4_0 = self.conv4_0(self.pool(x3_0))
#print('x4_0:',x4_0.shape)
x3_1 = self.conv3_1(torch.cat([x3_0, self.up(x4_0)], 1))
#print('x3_1:',x3_1.shape)
x2_2 = self.conv2_2(torch.cat([x2_0, x2_1, self.up(x3_1)], 1))
#print('x2_2:',x2_2.shape)
x1_3 = self.conv1_3(torch.cat([x1_0, x1_1, x1_2, self.up(x2_2)], 1))
#print('x1_3:',x1_3.shape)
x0_4 = self.conv0_4(torch.cat([x0_0, x0_1, x0_2, x0_3, self.up(x1_3)], 1))
# print('x0_4:',x0_4.shape)
if self.deep_supervision:
output1 = self.final1(x0_1)
output2 = self.final2(x0_2)
output3 = self.final3(x0_3)
output4 = self.final4(x0_4)
return [output1, output2, output3, output4]
else:
# 输出一个结果，结果是0~1之间
output = self.final(x0_4)
return output
if __name__ == '__main__':
#u=NestedUNet(2)
#input=torch.randn((1,3,512,512))
#a=u(input)
import torch
from torchsummary import summary
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using {device} device")
model = NestedUNet(2).to(device)
# 创建一个在GPU上的示例输入张量
example_input_size = (3, 512, 512) # 这是一个元组，代表输入张量的尺寸
summary(model, example_input_size)
deeplabv3
import math
import os
import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
BatchNorm2d = nn.BatchNorm2d
def conv_bn(inp, oup, stride):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
BatchNorm2d(oup),
nn.ReLU6(inplace=True) )
def conv_1x1_bn(inp, oup):
return nn.Sequential(
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
BatchNorm2d(oup),
nn.ReLU6(inplace=True) )
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, expand_ratio):
super(InvertedResidual, self).__init__()
self.stride = stride
assert stride in [1, 2]
hidden_dim = round(inp * expand_ratio)
self.use_res_connect = self.stride == 1 and inp == oup
if expand_ratio == 1:
self.conv = nn.Sequential(
#--------------------------------------------#
# 进行3x3的逐层卷积，进行跨特征点的特征提取
#--------------------------------------------#
nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
BatchNorm2d(hidden_dim),
nn.ReLU6(inplace=True),
#-----------------------------------#
# 利用1x1卷积进行通道数的调整
#-----------------------------------#
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
BatchNorm2d(oup),
)
else:
self.conv = nn.Sequential(
#-----------------------------------#
# 利用1x1卷积进行通道数的上升
#-----------------------------------#
nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
BatchNorm2d(hidden_dim),
nn.ReLU6(inplace=True),
#--------------------------------------------#
# 进行3x3的逐层卷积，进行跨特征点的特征提取
#--------------------------------------------#
nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
BatchNorm2d(hidden_dim),
nn.ReLU6(inplace=True),
#-----------------------------------#
# 利用1x1卷积进行通道数的下降
#-----------------------------------#
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
BatchNorm2d(oup),
)
def forward(self, x):
if self.use_res_connect:
return x + self.conv(x)
else:
return self.conv(x)
class MobileNetV2(nn.Module):
def __init__(self, n_class=1000, input_size=224, width_mult=1.):
super(MobileNetV2, self).__init__()
block = InvertedResidual
input_channel = 32
last_channel = 1280
interverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1], # 256, 256, 32 -> 256, 256, 16
[6, 24, 2, 2], # 256, 256, 16 -> 128, 128, 24 2
[6, 32, 3, 2], # 128, 128, 24 -> 64, 64, 32 4
[6, 64, 4, 2], # 64, 64, 32 -> 32, 32, 64 7
[6, 96, 3, 1], # 32, 32, 64 -> 32, 32, 96
[6, 160, 3, 2], # 32, 32, 96 -> 16, 16, 160 14
[6, 320, 1, 1], # 16, 16, 160 -> 16, 16, 320
]
assert input_size % 32 == 0
input_channel = int(input_channel * width_mult)
self.last_channel = int(last_channel * width_mult) if width_mult > 1.0 else last_channel
# 512, 512, 3 -> 256, 256, 32
self.features = [conv_bn(3, input_channel, 2)]
for t, c, n, s in interverted_residual_setting:
output_channel = int(c * width_mult)
for i in range(n):
if i == 0:
self.features.append(block(input_channel, output_channel, s, expand_ratio=t))
else:
self.features.append(block(input_channel, output_channel, 1, expand_ratio=t))
input_channel = output_channel
self.features.append(conv_1x1_bn(input_channel, self.last_channel))
self.features = nn.Sequential(*self.features)
self.classifier = nn.Sequential(
nn.Dropout(0.2),
nn.Linear(self.last_channel, n_class),
)
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = x.mean(3).mean(2)
x = self.classifier(x)
return x
def _initialize_weights(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))
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
elif isinstance(m, nn.Linear):
n = m.weight.size(1)
m.weight.data.normal_(0, 0.01)
m.bias.data.zero_()
def load_url(url, model_dir='./model_data', map_location=None):
if not os.path.exists(model_dir):
os.makedirs(model_dir)
filename = url.split('/')[-1]
cached_file = os.path.join(model_dir, filename)
if os.path.exists(cached_file):
return torch.load(cached_file, map_location=map_location)
else:
return model_zoo.load_url(url,model_dir=model_dir)
def mobilenetv2(pretrained=False, **kwargs):
model = MobileNetV2(n_class=1000, **kwargs)
if pretrained:
model.load_state_dict(load_url('https://github.com/bubbliiiing/deeplabv3-plus-pytorch/releases/download/v1.0/mobilenet_v2.pth.tar'), strict=False)
return model
if __name__ == "__main__":
model = mobilenetv2()
for i, layer in enumerate(model.features):
print(i, layer)
import torch
import torch.nn as nn
import torch.nn.functional as F
from .mobilenetv2 import mobilenetv2
class MobileNetV2(nn.Module):
def __init__(self, downsample_factor=8, ):
super(MobileNetV2, self).__init__()
from functools import partial
model = mobilenetv2(pretrained=False)
self.features = model.features[:-1]
self.total_idx = len(self.features)
self.down_idx = [2, 4, 7, 14]
if downsample_factor == 8:
for i in range(self.down_idx[-2], self.down_idx[-1]):
self.features[i].apply(
partial(self._nostride_dilate, dilate=2)
)
for i in range(self.down_idx[-1], self.total_idx):
self.features[i].apply(
partial(self._nostride_dilate, dilate=4)
)
elif downsample_factor == 16:
for i in range(self.down_idx[-1], self.total_idx):
self.features[i].apply(
partial(self._nostride_dilate, dilate=2)
)
def _nostride_dilate(self, m, dilate):
classname = m.__class__.__name__
if classname.find('Conv') != -1:
if m.stride == (2, 2):
m.stride = (1, 1)
if m.kernel_size == (3, 3):
m.dilation = (dilate // 2, dilate // 2)
m.padding = (dilate // 2, dilate // 2)
else:
if m.kernel_size == (3, 3):
m.dilation = (dilate, dilate)
m.padding = (dilate, dilate)
def forward(self, x):
low_level_features = self.features[:4](x)
x = self.features[4:](low_level_features)
return low_level_features, x
# -----------------------------------------#
# ASPP特征提取模块
# 利用不同膨胀率的膨胀卷积进行特征提取
# -----------------------------------------#
class ASPP(nn.Module):
def __init__(self, dim_in, dim_out, rate=1, bn_mom=0.1):
super(ASPP, self).__init__()
self.branch1 = nn.Sequential(
nn.Conv2d(dim_in, dim_out, 1, 1, padding=0, dilation=rate, bias=True),
nn.BatchNorm2d(dim_out, momentum=bn_mom),
nn.ReLU(inplace=True),
)
self.branch2 = nn.Sequential(
nn.Conv2d(dim_in, dim_out, 3, 1, padding=6 * rate, dilation=6 * rate, bias=True),
nn.BatchNorm2d(dim_out, momentum=bn_mom),
nn.ReLU(inplace=True),
)
self.branch3 = nn.Sequential(
nn.Conv2d(dim_in, dim_out, 3, 1, padding=12 * rate, dilation=12 * rate, bias=True),
nn.BatchNorm2d(dim_out, momentum=bn_mom),
nn.ReLU(inplace=True),
)
self.branch4 = nn.Sequential(
nn.Conv2d(dim_in, dim_out, 3, 1, padding=18 * rate, dilation=18 * rate, bias=True),
nn.BatchNorm2d(dim_out, momentum=bn_mom),
nn.ReLU(inplace=True),
)
self.branch5_conv = nn.Conv2d(dim_in, dim_out, 1, 1, 0, bias=True)
self.branch5_bn = nn.BatchNorm2d(dim_out, momentum=bn_mom)
self.branch5_relu = nn.ReLU(inplace=True)
self.conv_cat = nn.Sequential(
nn.Conv2d(dim_out * 5, dim_out, 1, 1, padding=0, bias=True),
nn.BatchNorm2d(dim_out, momentum=bn_mom),
nn.ReLU(inplace=True),
)
def forward(self, x):
[b, c, row, col] = x.size()
# -----------------------------------------#
# 一共五个分支
# -----------------------------------------#
conv1x1 = self.branch1(x)
conv3x3_1 = self.branch2(x)
conv3x3_2 = self.branch3(x)
conv3x3_3 = self.branch4(x)
# -----------------------------------------#
# 第五个分支，全局平均池化+卷积
# -----------------------------------------#
global_feature = torch.mean(x, 2, True)
global_feature = torch.mean(global_feature, 3, True)
global_feature = self.branch5_conv(global_feature)
global_feature = self.branch5_bn(global_feature)
global_feature = self.branch5_relu(global_feature)
global_feature = F.interpolate(global_feature, (row, col), None, 'bilinear', True)
# -----------------------------------------#
# 将五个分支的内容堆叠起来
# 然后1x1卷积整合特征。
# -----------------------------------------#
feature_cat = torch.cat([conv1x1, conv3x3_1, conv3x3_2, conv3x3_3, global_feature], dim=1)
result = self.conv_cat(feature_cat)
return result
class Unet(nn.Module):
def __init__(self, num_classes=2, downsample_factor=16,**kwargs):
super(Unet, self).__init__()
# ----------------------------------#
# 获得两个特征层
# 浅层特征 [128,128,24]
# 主干部分 [30,30,320]
# ----------------------------------#
self.backbone = MobileNetV2(downsample_factor=downsample_factor,)
in_channels = 320
low_level_channels = 24
# -----------------------------------------#
# ASPP特征提取模块
# 利用不同膨胀率的膨胀卷积进行特征提取
# -----------------------------------------#
self.aspp = ASPP(dim_in=in_channels, dim_out=256, rate=16 // downsample_factor)
# ----------------------------------#
# 浅层特征边
# ----------------------------------#
self.shortcut_conv = nn.Sequential(
nn.Conv2d(low_level_channels, 48, 1),
nn.BatchNorm2d(48),
nn.ReLU(inplace=True)
)
self.cat_conv = nn.Sequential(
nn.Conv2d(48 + 256, 256, 3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(256, 256, 3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(256, num_classes, 1, stride=1)
def forward(self, x):
H, W = x.size(2), x.size(3)
# -----------------------------------------#
# 获得两个特征层
# low_level_features: 浅层特征-进行卷积处理
# x : 主干部分-利用ASPP结构进行加强特征提取
# -----------------------------------------#
low_level_features, x = self.backbone(x)
x = self.aspp(x) #320,32,32 ---- 256,32,32
low_level_features = self.shortcut_conv(low_level_features) #24,128,128 ---- 48,128,128
# -----------------------------------------#
# 将加强特征边上采样
# 与浅层特征堆叠后利用卷积进行特征提取
# -----------------------------------------#
x = F.interpolate(x, size=(low_level_features.size(2), low_level_features.size(3)), mode='bilinear',
align_corners=True)
x = self.cat_conv(torch.cat((x, low_level_features), dim=1))
x = self.cls_conv(x)
x = F.interpolate(x, size=(H, W), mode='bilinear', align_corners=True)
return x
if __name__ == '__main__':
#u=NestedUNet(2)
#input=torch.randn((1,3,512,512))
#a=u(input)
import torch
from torchsummary import summary
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using {device} device")
model = Unet().to(device)
# 创建一个在GPU上的示例输入张量
example_input_size = (3, 512, 512) # 这是一个元组，代表输入张量的尺寸
summary(model, example_input_size)
attention-unet
import torch
import torch.nn as nn
import torch.nn.functional as F
class AttentionBlock(nn.Module):
def __init__(self, F_g, F_l, F_int):
super().__init__()
self.W_g = nn.Sequential(
nn.Conv2d(F_g, F_int, kernel_size=1, stride=1, padding=0, bias=True),
nn.BatchNorm2d(F_int))
self.W_x = nn.Sequential(
nn.Conv2d(F_l, F_int, kernel_size=1, stride=1, padding=0, bias=True),
nn.BatchNorm2d(F_int))
self.psi = nn.Sequential(
nn.Conv2d(F_int, 1, kernel_size=1, stride=1, padding=0, bias=True),
nn.BatchNorm2d(1), nn.Sigmoid())
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
def forward(self, g, x):
g1 = self.W_g(self.up(g))
x1 = self.W_x(x)
psi = F.relu(g1 + x1)
psi = self.psi(psi)
return x * psi
class VGGBlock(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channels, middle_channels, 3, padding=1),
nn.BatchNorm2d(middle_channels),
nn.ReLU(inplace=True),
nn.Conv2d(middle_channels, out_channels, 3, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True)
)
def forward(self, x):
return self.conv(x)
class Unet(nn.Module):
def __init__(self, num_classes=2, input_channels=3,**kwargs):
super().__init__()
#nb_filter = [32, 64, 128, 256, 512] # Total params: 7,852,578 Params size (MB): 30.46
nb_filter = [64, 128, 256, 512, 512] # Total params:19,591,234 Params size (MB): 76.24
self.pool = nn.MaxPool2d(2, 2)
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv3_1 = VGGBlock(nb_filter[4] + nb_filter[3], nb_filter[3], nb_filter[3])
self.conv2_2 = VGGBlock(nb_filter[3] + nb_filter[2], nb_filter[2], nb_filter[2])
self.conv1_3 = VGGBlock(nb_filter[2] + nb_filter[1], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock(nb_filter[1] + nb_filter[0], nb_filter[0], nb_filter[0])
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.att43 = AttentionBlock(nb_filter[4], nb_filter[3], nb_filter[3]//2)
self.att32 = AttentionBlock(nb_filter[3], nb_filter[2], nb_filter[2]//2)
self.att21 = AttentionBlock(nb_filter[2], nb_filter[1], nb_filter[1]//2)
self.att10 = AttentionBlock(nb_filter[1], nb_filter[0], nb_filter[0]//2)
def forward(self, input):
x0_0 = self.conv0_0(input)
x1_0 = self.conv1_0(self.pool(x0_0))
x2_0 = self.conv2_0(self.pool(x1_0))
x3_0 = self.conv3_0(self.pool(x2_0))
x4_0 = self.conv4_0(self.pool(x3_0))
# 在上采样和卷积块之间插入注意力模块
x3_1 = self.conv3_1(torch.cat([self.att43(x4_0, x3_0), self.up(x4_0)], 1))
x2_2 = self.conv2_2(torch.cat([self.att32(x3_1, x2_0), self.up(x3_1)], 1))
x1_3 = self.conv1_3(torch.cat([self.att21(x2_2, x1_0), self.up(x2_2)], 1))
x0_4 = self.conv0_4(torch.cat([self.att10(x1_3, x0_0), self.up(x1_3)], 1))
output = self.final(x0_4)
return output
if __name__ == '__main__':
from torchsummary import summary
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using {device} device")
# 创建模型实例并将其移动到相应的设备上
model = AttentionUNet().to(device)
# 打印模型结构
print(model)
# 创建一个在GPU上的示例输入张量
example_input_size = (3, 512, 512) # 这是一个元组，代表输入张量的尺寸
# 使用torchsummary来展示模型的摘要
summary(model, example_input_size)
