1、Backbone
import torch
import torch.nn as nn
def conv_bn(inp, oup, stride=1):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU6()
)
def conv_dw(inp, oup, stride=1):
return nn.Sequential(
nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
nn.BatchNorm2d(inp),
nn.ReLU6(),
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU6(),
)
class MobileNetV1(nn.Module):
def __init__(self):
super(MobileNetV1, self).__init__()
self.stage1 = nn.Sequential(
# 160,160,3 -> 80,80,32
conv_bn(3, 32, 2),
# 80,80,32 -> 80,80,64
conv_dw(32, 64, 1),
# 80,80,64 -> 40,40,128
conv_dw(64, 128, 2),
conv_dw(128, 128, 1),
# 40,40,128 -> 20,20,256
conv_dw(128, 256, 2),
conv_dw(256, 256, 1),
)
self.stage2 = nn.Sequential(
# 20,20,256 -> 10,10,512
conv_dw(256, 512, 2),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
)
self.stage3 = nn.Sequential(
# 10,10,512 -> 5,5,1024
conv_dw(512, 1024, 2),
conv_dw(1024, 1024, 1),
)
self.avg = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(1024, 1000)
def forward(self, x):
x = self.stage1(x)
x = self.stage2(x)
x = self.stage3(x)
x = self.avg(x)
print("self.avg(x):", x.size())
# x = self.model(x)
x = x.view(-1, 1024)
x = self.fc(x)
return x
if __name__ == '__main__':
x = torch.randn(10, 3, 640, 640)
x = MobileNetV1()(x)
print(x.size())
输出:
self.avg(x): torch.Size([10, 1024, 1, 1])
torch.Size([10, 1000])
2、根据Backbone获取的特征获得长度为128的特征向量
下面的python代码是manu04.py文件中的全部代码
from torch import nn
def conv_bn(inp, oup, stride=1):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU6()
)
def conv_dw(inp, oup, stride=1):
return nn.Sequential(
nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
nn.BatchNorm2d(inp),
nn.ReLU6(),
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
nn.ReLU6(),
)
class MobileNetV1(nn.Module):
def __init__(self):
super(MobileNetV1, self).__init__()
self.stage1 = nn.Sequential(
# 160,160,3 -> 80,80,32
conv_bn(3, 32, 2),
# 80,80,32 -> 80,80,64
conv_dw(32, 64, 1),
# 80,80,64 -> 40,40,128
conv_dw(64, 128, 2),
conv_dw(128, 128, 1),
# 40,40,128 -> 20,20,256
conv_dw(128, 256, 2),
conv_dw(256, 256, 1),
)
self.stage2 = nn.Sequential(
# 20,20,256 -> 10,10,512
conv_dw(256, 512, 2),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
)
self.stage3 = nn.Sequential(
# 10,10,512 -> 5,5,1024
conv_dw(512, 1024, 2),
conv_dw(1024, 1024, 1),
)
self.avg = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(1024, 1000)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.normal_(m.weight, 0, 0.1)
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def forward(self, x):
x = self.stage1(x)
x = self.stage2(x)
x = self.stage3(x)
x = self.avg(x)
# x = self.model(x)
x = x.view(-1, 1024)
x = self.fc(x)
return x
class mobilenet(nn.Module):
def __init__(self):
super(mobilenet, self).__init__()
self.model = MobileNetV1()
# if pretrained:
# state_dict = load_state_dict_from_url(
# "https://github.com/bubbliiiing/facenet-pytorch/releases/download/v1.0/backbone_weights_of_mobilenetv1.pth",
# model_dir="model_data",
# progress=True)
# self.model.load_state_dict(state_dict)
del self.model.fc
del self.model.avg
def forward(self, x):
x = self.model.stage1(x)
x = self.model.stage2(x)
x = self.model.stage3(x)
return x
class mobilenet(nn.Module):
def __init__(self):
super(mobilenet, self).__init__()
self.model = MobileNetV1()
# if pretrained:
# state_dict = load_state_dict_from_url(
# "https://github.com/bubbliiiing/facenet-pytorch/releases/download/v1.0/backbone_weights_of_mobilenetv1.pth",
# model_dir="model_data",
# progress=True)
# self.model.load_state_dict(state_dict)
del self.model.fc
del self.model.avg
def forward(self, x):
x = self.model.stage1(x)
x = self.model.stage2(x)
x = self.model.stage3(x)
return x
下面的代码是manu01.py的全部代码
import torch
from torch import nn
import torch.nn.functional as F
from manu04 import mobilenet
class Facenet(nn.Module):
def __init__(self, backbone="mobilenet", dropout_keep_prob=0.5, embedding_size=128, num_classes=None, mode="train"):
super(Facenet, self).__init__()
if backbone == "mobilenet":
self.backbone = mobilenet()
flat_shape = 1024
# elif backbone == "inception_resnetv1":
# self.backbone = inception_resnet()
# flat_shape = 1792
else:
raise ValueError('Unsupported backbone - `{}`, Use mobilenet, inception_resnetv1.'.format(backbone))
self.avg = nn.AdaptiveAvgPool2d((1, 1))
self.Dropout = nn.Dropout(1 - dropout_keep_prob)
self.Bottleneck = nn.Linear(flat_shape, embedding_size, bias=False)
self.last_bn = nn.BatchNorm1d(embedding_size, eps=0.001, momentum=0.1, affine=True)
if mode == "train":
self.classifier = nn.Linear(embedding_size, num_classes)
def forward(self, x):
x = self.backbone(x)
print("self.backbone shape:", x.size())
x = self.avg(x)
print("self.avg shape:", x.size())
x = x.view(x.size(0), -1)
print("x.view(x.size(0), -1) shape:", x.size())
x = self.Dropout(x)
x = self.Bottleneck(x)
x = self.last_bn(x)
x = F.normalize(x, p=2, dim=1)
return x
def forward_feature(self, x):
x = self.backbone(x)
x = self.avg(x)
x = x.view(x.size(0), -1)
x = self.Dropout(x)
x = self.Bottleneck(x)
before_normalize = self.last_bn(x)
# F.normalize,refer:https://blog.csdn.net/lj2048/article/details/118115681?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522169268543416800197051503%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.%2522%257D&request_id=169268543416800197051503&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~first_rank_ecpm_v1~hot_rank-1-118115681-null-null.142^v93^chatsearchT3_2&utm_term=F.normalize&spm=1018.2226.3001.4187
x = F.normalize(before_normalize, p=2, dim=1)
return before_normalize, x
def forward_classifier(self, x):
x = self.classifier(x)
return x
if __name__ == '__main__':
x = torch.randn(10, 3, 640, 640)
x = Facenet(num_classes=20)(x)
print(x.size())
输出:
self.backbone shape: torch.Size([10, 1024, 20, 20])
self.avg shape: torch.Size([10, 1024, 1, 1])
x.view(x.size(0), -1) shape: torch.Size([10, 1024])
torch.Size([10, 128])