4.Mobilenetv2网络的简单目标识别的实现

1.首先建立一个model.py文件，用来写神经网络，代码如下：

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):#groups=1普通卷积
        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)
        )

#到残差结构
class InvertedResidual(nn.Module):
    def __init__(self, in_channel, out_channel, stride, expand_ratio):#expand_ratio扩展因子
        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):#alpha超参数
        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.下载数据集

DATA_URL = 'http://download.tensorflow.org/example_images/flower_photos.tgz'

3.下载完后写一个spile_data.py文件，将数据集进行分类

#spile_data.py
 
import os
from shutil import copy
import random
 
 
def mkfile(file):
    if not os.path.exists(file):
        os.makedirs(file)
 
 
file = 'flower_data/flower_photos'
flower_class = [cla for cla in os.listdir(file) if ".txt" not in cla]
mkfile('flower_data/train')
for cla in flower_class:
    mkfile('flower_data/train/'+cla)
 
mkfile('flower_data/val')
for cla in flower_class:
    mkfile('flower_data/val/'+cla)
 
split_rate = 0.1
for cla in flower_class:
    cla_path = file + '/' + cla + '/'
    images = os.listdir(cla_path)
    num = len(images)
    eval_index = random.sample(images, k=int(num*split_rate))
    for index, image in enumerate(images):
        if image in eval_index:
            image_path = cla_path + image
            new_path = 'flower_data/val/' + cla
            copy(image_path, new_path)
        else:
            image_path = cla_path + image
            new_path = 'flower_data/train/' + cla
            copy(image_path, new_path)
        print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing bar
    print()
 
print("processing done!")

之后应该是这样：

4.再写一个train.py文件，用来训练模型

import torch
import torch.nn as nn
from torchvision import transforms, datasets
import json
import os
import torch.optim as optim
from model import MobileNetV2
import torchvision.models.mobilenet

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)

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.getcwd() # get data root path
image_path = data_root + "/flower_data/"  # flower data set path

train_dataset = datasets.ImageFolder(root=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)

batch_size = 16

train_loader = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size, shuffle=True,
                                           num_workers=0)

validate_dataset = datasets.ImageFolder(root=image_path + "val",
                                        transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
                                              batch_size=batch_size, shuffle=False,
                                              num_workers=0)

net = MobileNetV2(num_classes=5)
# load pretrain weights


# load pretrain weights
model_weight_path = "./mobilenet_v2.pth"
pre_weights = torch.load(model_weight_path)
# delete classifier weights
pre_dict = {k: v for k, v in pre_weights.items() if "classifier" not in k}
missing_keys, unexpected_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)

loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0001)

best_acc = 0.0
save_path = './MobileNetV2.pth'

for epoch in range(5):
    # train
    net.train()
    running_loss = 0.0
    for step, data in enumerate(train_loader, start=0):
        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()
        # print train process
        rate = (step+1)/len(train_loader)
        a = "*" * int(rate * 50)
        b = "." * int((1 - rate) * 50)
        print("\rtrain loss: {:^3.0f}%[{}->{}]{:.4f}".format(int(rate*100), a, b, loss), end="")
    print()

# validate
    net.eval()
    acc = 0.0  # accumulate accurate number / epoch
    with torch.no_grad():
        for val_data in validate_loader:
            val_images, val_labels = val_data
            outputs = net(val_images.to(device))  # eval model only have last output layer
            # loss = loss_function(outputs, test_labels)
            predict_y = torch.max(outputs, dim=1)[1]
            acc += (predict_y == val_labels.to(device)).sum().item()
        val_accurate = acc / val_num
        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)
        print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f' %
              (epoch + 1, running_loss / step, val_accurate))

print('Finished Training')

5.写一个预测的predict.py文件

代码如下：

import torch
from model import MobileNetV2
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import json

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 = Image.open("sunflower.jpg")
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)

# read class_indic
try:
    json_file = open('./class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)

# create model
model = MobileNetV2(num_classes=5)
# load model weights
model_weight_path = "./MobileNetV2.pth"
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():
    # predict class
    output = torch.squeeze(model(img))
    predict = torch.softmax(output, dim=0)
    predict_cla = torch.argmax(predict).numpy()
print(class_indict[str(predict_cla)], predict[predict_cla].numpy())
plt.show()