MobileNet v1、v2，v3网络模型
1.网络模型整体架构
1.1.MobileNet v1网络
MobileNet v1网络是由Google团队在2017年提出的，专注于移动端或者嵌入式设备中的轻量级CNN网络。相比传统卷积神经网络，在准确率小幅降低的前提下大大减少模型参数与运算量。（相比VGG16准确率减小了0.9%，但模型参数只有VGG的1/32）。网络中的亮点有：
- Depthwise Convolution（大大减少运算量和参数数量）
- 增加超参数α、β
mobilenet v1网络模型
1.2.MobileNet v2网络
MobileNet v2网络时Google团队在2018年提出的，相比MobileNet v1网络，准确率更高，模型更小。网络中的亮点有：
- Inverted Residuals（倒残差结构）
- Linear Bottlenecks
mobilenet v2网络模型
- t是扩展因子
- c是输出特征矩阵深度channel
- n是bottleneck的重复次数
- s是步距（针对第一层，其他为1）
1.3.MobileNet v3网络
- 更新Block（bneck）：加入SE模块，更新了激活函数
- 使用NAS搜索参数（Neural Architecture Search）
- 重新设计耗时层结构：减少第一个卷积层的卷积核个数（32→16），精简Last stage
- 注意：当stride==1且input_channel==output_channel才有shortcut连接
MobileNet v3-large网络
MobileNet v3-small网络
2.网络模型搭建
2.1.MobileNetV2网络
from torch import nn
import torch
def _make_divisible(ch, divisor=8, min_ch=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
class ConvBNReLU(nn.Sequential):
def __init__(self, in_channel, out_channel, kernel_size=3, stride=1, groups=1):
padding = (kernel_size - 1) // 2
super(ConvBNReLU, self).__init__(
nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, groups=groups, bias=False),
nn.BatchNorm2d(out_channel),
nn.ReLU6(inplace=True)
)
class InvertedResidual(nn.Module):
def __init__(self, in_channel, out_channel, stride, expand_ratio):
super(InvertedResidual, self).__init__()
hidden_channel = in_channel * expand_ratio
self.use_shortcut = stride == 1 and in_channel == out_channel
layers = []
if expand_ratio != 1:
# 1x1 pointwise conv
layers.append(ConvBNReLU(in_channel, hidden_channel, kernel_size=1))
layers.extend([
# 3x3 depthwise conv
ConvBNReLU(hidden_channel, hidden_channel, stride=stride, groups=hidden_channel),
# 1x1 pointwise conv(linear)
nn.Conv2d(hidden_channel, out_channel, kernel_size=1, bias=False),
nn.BatchNorm2d(out_channel),
])
self.conv = nn.Sequential(*layers)
def forward(self, x):
if self.use_shortcut:
return x + self.conv(x)
else:
return self.conv(x)
class MobileNetV2(nn.Module):
def __init__(self, num_classes=1000, alpha=1.0, round_nearest=8):
super(MobileNetV2, self).__init__()
block = InvertedResidual
input_channel = _make_divisible(32 * alpha, round_nearest)
last_channel = _make_divisible(1280 * alpha, round_nearest)
inverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
features = []
# conv1 layer
features.append(ConvBNReLU(3, input_channel, stride=2))
# building inverted residual residual blockes
for t, c, n, s in inverted_residual_setting:
output_channel = _make_divisible(c * alpha, round_nearest)
for i in range(n):
stride = s if i == 0 else 1
features.append(block(input_channel, output_channel, stride, expand_ratio=t))
input_channel = output_channel
# building last several layers
features.append(ConvBNReLU(input_channel, last_channel, 1))
# combine feature layers
self.features = nn.Sequential(*features)
# building classifier
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.classifier = nn.Sequential(
nn.Dropout(0.2),
nn.Linear(last_channel, num_classes)
)
# weight initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.BatchNorm2d):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def forward(self, x):
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
2.2.MobileNetV3网络
from typing import Callable, List, Optional
import torch
from torch import nn, Tensor
from torch.nn import functional as F
from functools import partial
def _make_divisible(ch, divisor=8, min_ch=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
class ConvBNActivation(nn.Sequential):
def __init__(self,
in_planes: int,
out_planes: int,
kernel_size: int = 3,
stride: int = 1,
groups: int = 1,
norm_layer: Optional[Callable[..., nn.Module]] = None,
activation_layer: Optional[Callable[..., nn.Module]] = None):
padding = (kernel_size - 1) // 2
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if activation_layer is None:
activation_layer = nn.ReLU6
super(ConvBNActivation, self).__init__(nn.Conv2d(in_channels=in_planes,
out_channels=out_planes,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias=False),
norm_layer(out_planes),
activation_layer(inplace=True))
class SqueezeExcitation(nn.Module):
def __init__(self, input_c: int, squeeze_factor: int = 4):
super(SqueezeExcitation, self).__init__()
squeeze_c = _make_divisible(input_c // squeeze_factor, 8)
self.fc1 = nn.Conv2d(input_c, squeeze_c, 1)
self.fc2 = nn.Conv2d(squeeze_c, input_c, 1)
def forward(self, x: Tensor) -> Tensor:
scale = F.adaptive_avg_pool2d(x, output_size=(1, 1))
scale = self.fc1(scale)
scale = F.relu(scale, inplace=True)
scale = self.fc2(scale)
scale = F.hardsigmoid(scale, inplace=True)
return scale * x
class InvertedResidualConfig:
def __init__(self,
input_c: int,
kernel: int,
expanded_c: int,
out_c: int,
use_se: bool,
activation: str,
stride: int,
width_multi: float):
self.input_c = self.adjust_channels(input_c, width_multi)
self.kernel = kernel
self.expanded_c = self.adjust_channels(expanded_c, width_multi)
self.out_c = self.adjust_channels(out_c, width_multi)
self.use_se = use_se
self.use_hs = activation == "HS" # whether using h-swish activation
self.stride = stride
@staticmethod
def adjust_channels(channels: int, width_multi: float):
return _make_divisible(channels * width_multi, 8)
class InvertedResidual(nn.Module):
def __init__(self,
cnf: InvertedResidualConfig,
norm_layer: Callable[..., nn.Module]):
super(InvertedResidual, self).__init__()
if cnf.stride not in [1, 2]:
raise ValueError("illegal stride value.")
self.use_res_connect = (cnf.stride == 1 and cnf.input_c == cnf.out_c)
layers: List[nn.Module] = []
activation_layer = nn.Hardswish if cnf.use_hs else nn.ReLU
# expand
if cnf.expanded_c != cnf.input_c:
layers.append(ConvBNActivation(cnf.input_c,
cnf.expanded_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=activation_layer))
# depthwise
layers.append(ConvBNActivation(cnf.expanded_c,
cnf.expanded_c,
kernel_size=cnf.kernel,
stride=cnf.stride,
groups=cnf.expanded_c,
norm_layer=norm_layer,
activation_layer=activation_layer))
if cnf.use_se:
layers.append(SqueezeExcitation(cnf.expanded_c))
# project
layers.append(ConvBNActivation(cnf.expanded_c,
cnf.out_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Identity))
self.block = nn.Sequential(*layers)
self.out_channels = cnf.out_c
self.is_strided = cnf.stride > 1
def forward(self, x: Tensor) -> Tensor:
result = self.block(x)
if self.use_res_connect:
result += x
return result
class MobileNetV3(nn.Module):
def __init__(self,
inverted_residual_setting: List[InvertedResidualConfig],
last_channel: int,
num_classes: int = 1000,
block: Optional[Callable[..., nn.Module]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None):
super(MobileNetV3, self).__init__()
if not inverted_residual_setting:
raise ValueError("The inverted_residual_setting should not be empty.")
elif not (isinstance(inverted_residual_setting, List) and
all([isinstance(s, InvertedResidualConfig) for s in inverted_residual_setting])):
raise TypeError("The inverted_residual_setting should be List[InvertedResidualConfig]")
if block is None:
block = InvertedResidual
if norm_layer is None:
norm_layer = partial(nn.BatchNorm2d, eps=0.001, momentum=0.01)
layers: List[nn.Module] = []
# building first layer
firstconv_output_c = inverted_residual_setting[0].input_c
layers.append(ConvBNActivation(3,
firstconv_output_c,
kernel_size=3,
stride=2,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
# building inverted residual blocks
for cnf in inverted_residual_setting:
layers.append(block(cnf, norm_layer))
# building last several layers
lastconv_input_c = inverted_residual_setting[-1].out_c
lastconv_output_c = 6 * lastconv_input_c
layers.append(ConvBNActivation(lastconv_input_c,
lastconv_output_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
self.features = nn.Sequential(*layers)
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.classifier = nn.Sequential(nn.Linear(lastconv_output_c, last_channel),
nn.Hardswish(inplace=True),
nn.Dropout(p=0.2, inplace=True),
nn.Linear(last_channel, num_classes))
# initial weights
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out")
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def _forward_impl(self, x: Tensor) -> Tensor:
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
def forward(self, x: Tensor) -> Tensor:
return self._forward_impl(x)
def mobilenet_v3_large(num_classes: int = 1000,
reduced_tail: bool = False) -> MobileNetV3:
"""
Constructs a large MobileNetV3 architecture from
"Searching for MobileNetV3" .
weights_link:
https://download.pytorch.org/models/mobilenet_v3_large-8738ca79.pth
Args:
num_classes (int): number of classes
reduced_tail (bool): If True, reduces the channel counts of all feature layers
between C4 and C5 by 2. It is used to reduce the channel redundancy in the
backbone for Detection and Segmentation.
"""
width_multi = 1.0
bneck_conf = partial(InvertedResidualConfig, width_multi=width_multi)
adjust_channels = partial(InvertedResidualConfig.adjust_channels, width_multi=width_multi)
reduce_divider = 2 if reduced_tail else 1
inverted_residual_setting = [
# input_c, kernel, expanded_c, out_c, use_se, activation, stride
bneck_conf(16, 3, 16, 16, False, "RE", 1),
bneck_conf(16, 3, 64, 24, False, "RE", 2), # C1
bneck_conf(24, 3, 72, 24, False, "RE", 1),
bneck_conf(24, 5, 72, 40, True, "RE", 2), # C2
bneck_conf(40, 5, 120, 40, True, "RE", 1),
bneck_conf(40, 5, 120, 40, True, "RE", 1),
bneck_conf(40, 3, 240, 80, False, "HS", 2), # C3
bneck_conf(80, 3, 200, 80, False, "HS", 1),
bneck_conf(80, 3, 184, 80, False, "HS", 1),
bneck_conf(80, 3, 184, 80, False, "HS", 1),
bneck_conf(80, 3, 480, 112, True, "HS", 1),
bneck_conf(112, 3, 672, 112, True, "HS", 1),
bneck_conf(112, 5, 672, 160 // reduce_divider, True, "HS", 2), # C4
bneck_conf(160 // reduce_divider, 5, 960 // reduce_divider, 160 // reduce_divider, True, "HS", 1),
bneck_conf(160 // reduce_divider, 5, 960 // reduce_divider, 160 // reduce_divider, True, "HS", 1),
]
last_channel = adjust_channels(1280 // reduce_divider) # C5
return MobileNetV3(inverted_residual_setting=inverted_residual_setting,
last_channel=last_channel,
num_classes=num_classes)
def mobilenet_v3_small(num_classes: int = 1000,
reduced_tail: bool = False) -> MobileNetV3:
"""
Constructs a large MobileNetV3 architecture from
"Searching for MobileNetV3" .
weights_link:
https://download.pytorch.org/models/mobilenet_v3_small-047dcff4.pth
Args:
num_classes (int): number of classes
reduced_tail (bool): If True, reduces the channel counts of all feature layers
between C4 and C5 by 2. It is used to reduce the channel redundancy in the
backbone for Detection and Segmentation.
"""
width_multi = 1.0
bneck_conf = partial(InvertedResidualConfig, width_multi=width_multi)
adjust_channels = partial(InvertedResidualConfig.adjust_channels, width_multi=width_multi)
reduce_divider = 2 if reduced_tail else 1
inverted_residual_setting = [
# input_c, kernel, expanded_c, out_c, use_se, activation, stride
bneck_conf(16, 3, 16, 16, True, "RE", 2), # C1
bneck_conf(16, 3, 72, 24, False, "RE", 2), # C2
bneck_conf(24, 3, 88, 24, False, "RE", 1),
bneck_conf(24, 5, 96, 40, True, "HS", 2), # C3
bneck_conf(40, 5, 240, 40, True, "HS", 1),
bneck_conf(40, 5, 240, 40, True, "HS", 1),
bneck_conf(40, 5, 120, 48, True, "HS", 1),
bneck_conf(48, 5, 144, 48, True, "HS", 1),
bneck_conf(48, 5, 288, 96 // reduce_divider, True, "HS", 2), # C4
bneck_conf(96 // reduce_divider, 5, 576 // reduce_divider, 96 // reduce_divider, True, "HS", 1),
bneck_conf(96 // reduce_divider, 5, 576 // reduce_divider, 96 // reduce_divider, True, "HS", 1)
]
last_channel = adjust_channels(1024 // reduce_divider) # C5
return MobileNetV3(inverted_residual_setting=inverted_residual_setting,
last_channel=last_channel,
num_classes=num_classes)
3.网络模型训练
import os
import sys
import json
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import transforms,datasets
from tqdm import tqdm
from model_v2 import MobileNetV2
def main():
device = torch.device("cuda:0"if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
batch_size = 16
epochs = 5
data_transform = {
"train":transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
"val":transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])
])
}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = os.path.join(data_root,"000000\pytorch_图像分类\deep-learning-for-image-processing-master\data_set","flower_data")
assert os.path.exists(image_path),"{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path,"train"),transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val,key) for key,val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict,indent=4)
with open ('class_indices.json','w') as json_file:
json_file.write(json_str)
nw = min([os.cpu_count(),batch_size if batch_size > 1 else 0,8]) # number of workers
print("Using {} dataloader workers every process.".format(nw))
train_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size,
shuffle=True,
num_workers=nw
)
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path,"val"),transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(
validate_dataset,
batch_size,
shuffle=False,
num_workers=nw
)
print("using {} images for training,{} images for validation.".format(train_num,val_num))
# create model
net = MobileNetV2(num_classes=5)
# load pretrain weights
# download url: https://download.pytorch.org/models/mobilenet_v2-b0353104.pth
model_weight_path = "./mobilenet_v2.pth"
assert os.path.exists(model_weight_path),"file {} does not exist.".format(model_weight_path)
pre_weights = torch.load(model_weight_path,map_location='cpu')
# delete classifier weights
pre_dict = {k:v for k,v in pre_weights.items() if net.state_dict()[k].numel() == v.numel()}
missing_keys,unexpect_keys = net.load_state_dict(pre_dict,strict=False)
# freeze features weights
for param in net.features.parameters():
param.requires_grad = False
net.to(device)
# define loss function
loss_function = nn.CrossEntropyLoss()
# construct an optimizer
params = [p for p in net.parameters() if p.requires_grad]
optimizer = optim.Adam(params,lr=0.0001)
best_acc = 0.0
save_path = './MobileNetV2.pth'
train_steps = len(train_loader)
# print(train_steps)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader,file=sys.stdout)
for step,data in enumerate(train_bar):
images,labels = data
optimizer.zero_grad()
logits = net(images.to(device))
loss = loss_function(logits,labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch+1,epochs,loss)
# validate
net.eval()
acc = 0.0 # accumalate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader,file=sys.stdout)
for val_data in val_bar:
val_images,val_labels = val_data
outputs = net(val_images.to(device))
# loss = loss_function(outputs,val_labels)
predict_y = torch.max(outputs,dim=1)[1]
acc += torch.eq(predict_y,val_labels.to(device)).sum().item()
val_bar.desc = "valid epoch[{}/{}]".format(epoch+1,epochs)
val_accurate = acc/val_num
print("[epoch %d] train loss:%.3f val_accuracy:%.3f"%(epoch+1,running_loss/train_steps,val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(),save_path)
print("Finished Training!!")
if __name__ == "__main__":
main()4.模型检验
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model_v2 import MobileNetV2
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("use {} device.".format(device))
data_transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])
])
# load image
img_path = "./tulip.jpg"
assert os.path.exists(img_path),"file:'{}'does not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
#[N,C,H,W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img,dim=0)
# read class indict
json_path = "./class_indices.json"
assert os.path.exists(json_path),"file:'{}'does not exist.".format(json_path)
with open(json_path,'r') as f:
class_indict = json.load(f)
# create model
model = MobileNetV2(num_classes=5).to(device)
# load model weights
model_weight_path = "./MobileNetV2.pth"
assert os.path.exists(model_weight_path),"file:'{}'does not exist.".format(model_weight_path)
model.load_state_dict(torch.load(model_weight_path,map_location=device))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output,dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class:{} prob:{:.3}".format(class_indict[str(predict_cla)],predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class:{:10} prob:{:.3f}".format(class_indict[str(i)],predict[i].numpy()))
plt.show()
if __name__ == "__main__":
main()