目录

一、网络结构

二、创新点分析

三、知识点

1. nn.ReLU(inplace) 

2. os.getcwd与os.path.abspath 

3. 使用torchvision下的datasets包 

4. items()与dict()用法 

5. json文件  

6. tqdm

7. net.train()与net.val()

四、代码

---

AlexNet是由Alex Krizhevsky、Ilya Sutskever和Geoffrey Hinton在2012年ImageNet图像分类竞赛中提出的一种经典的卷积神经网络。AlexNet使用了Dropout层，减少过拟合现象的发生。

一、网络结构

二、数据集 

文件存放：

dataset->flower_data->flower_photos

再使用split_data.py 将数据集根据比例划分成训练集和预测集

详细请查看b站up主霹雳吧啦Wz：https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/blob/master/pytorch_classification

三、创新点分析

1. deeper网络结构

    通过增加网络深度，AlexNet可以更好的学习数据集的特征，并提高分类的准确率。

2. 使用ReLU激活函数，克服梯度消失以及求梯度复杂的问题。

3. 使用LRN局部响应归一化

    LRN是在卷积与池化层间添加归一化操作。卷积过程中，每个卷积核都对应一个feature map，LRN对这些feature map进行归一化操作。即，对每个特征图的每个位置，计算该位置周围的像素平方和，然后将当前位置像素值除以这个和。LRN可抑制邻近神经元的响应，在一定程度上能够避免过拟合，提高网络泛化能力。

4. 使用Dropout层

Dropout层：在训练过程中随机删除一定比例的神经元，以减少过拟合。Dropout一般放在全连接层与全连接层之间。

四、知识点

1. nn.ReLU(inplace) 默认参数为：inplace=False

inplace=False：不会修改输入对象的值，而是返回一个新创建的对象，即打印出的对象存储地址不同。（值传递）

inplace=True：会修改输入对象的值，即打印的对象存储地址相同，可以节省申请与释放内存的空间与时间。（地址传递）

import torch
import numpy as np
import torch.nn as nn# id()方法返回对象的内存地址
relu1 = nn.ReLU(inplace=False)
relu2 = nn.ReLU(inplace=True)
data = np.random.randn(2, 4)
input = torch.from_numpy(data)  # 转换成tensor类型
print("input address:", id(input))
output1 = relu1(input)
print("replace=False -- output address:", id(output1))
output2 = relu2(input)
print("replace=True -- output address:", id(output2))
# input address: 1669839583200
# replace=False -- output address: 1669817512352
# replace=True -- output address: 1669839583200

2. os.getcwd与os.path.abspath 

os.getcwd()：获取当前工作目录

os.path.abspath('xxx.py')：获取文件当前的完整路径

import osprint(os.getcwd())  # D:\Code
print(os.path.abspath('test.py'))  # D:\Code\test.py

3. 使用torchvision下的datasets包 

train_dataset=datasets.ImageFolder(root=os.path.join(image_path,'train'),transform=data_transform['train'])

可以得出这些信息： 

4. items()与dict()用法 

items()：把字典中的每对key和value组成一个元组，并将这些元组放在列表中返回。

obj = {'dog': 0,'cat': 1,'fish': 2
}
print(obj)  # {'dog': 0, 'cat': 1, 'fish': 2}
print(obj.items())  # dict_items([('dog', 0), ('cat', 1), ('fish', 2)])
print(dict((v, k) for k, v in obj.items()))  # {0: 'dog', 1: 'cat', 2: 'fish'}

5. json文件  

（1）json.dumps：将Python对象编码成JSON字符串

（2）json.loads：将已编码的JSON字符串编码为Python对象

import jsondata = [1, 2, 3]
data_json = json.dumps(data)  # <class 'str'>
data = json.loads(data_json)
print(type(data))  # <class 'list'>

6. tqdm

train_bar = tqdm(train_loader, file=sys.stdout)
使用tqdm函数，对train_loader进行迭代，将进度条输出到标准输出流sys.stdout中。可以方便用户查看训练进度。

from tqdm import tqdm
import timefor i in tqdm(range(10)):time.sleep(0.1)

7. net.train()与net.val()

net.train()：启用BatchNormalization和Dropout

net.eval|()：不启用BatchNormalization和Dropout

五、代码

model.py

import torch
import torch.nn as nnclass AlexNet(nn.Module):def __init__(self, num_classes=1000):super(AlexNet, self).__init__()self.features = nn.Sequential(nn.Conv2d(3, 96, kernel_size=11, padding=2, stride=4),  # input[3,224,224] output[96,55,55]nn.ReLU(inplace=True),  # inplace=True 址传递nn.MaxPool2d(kernel_size=3, stride=2),  # output[96,27,27]nn.Conv2d(96, 256, kernel_size=5, padding=2),  # output[256,27,27]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2),  # output[256,13,13]nn.Conv2d(256, 384, kernel_size=3, padding=1),  # output[384,13,13]nn.ReLU(inplace=True),nn.Conv2d(384, 384, kernel_size=3, padding=1),  # output[384,13,13]nn.ReLU(inplace=True),nn.Conv2d(384, 256, kernel_size=3, padding=1),  # output[256,13,13]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2),  # output[256,6,6])self.classifier = nn.Sequential(nn.Dropout(p=0.5),nn.Linear(256 * 6 * 6, 2048),nn.ReLU(inplace=True),nn.Dropout(p=0.5),nn.Linear(2048, 2048),nn.ReLU(inplace=True),nn.Linear(2048, num_classes))def forward(self, x):x = self.features(x)x = torch.flatten(x, start_dim=1)  # batch这一维度不用，从channel开始x = self.classifier(x)return x

train.py 

import os
import torch
import torch.nn as nn
from torchvision import transforms, datasets
import json
from model import AlexNet
import torch.optim as optim
from tqdm import tqdmdef main():device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')print("using:{}".format(device))data_transform = {'train': transforms.Compose([# 将给定图像随机裁剪为不同的大小和宽高比，然后缩放所裁剪得到的图像为指定大小transforms.RandomResizedCrop(224),# 水平方向随机翻转transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),'val': transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}# get data root pathdata_root = os.path.abspath(os.getcwd())  # D:\Code\AlexNet# get flower data set pathimage_path = os.path.join(data_root, 'data_set', 'flower_data')  # D:\Code\AlexNet\data_set\flower_data# 使用assert断言语句：出现错误条件时，就触发异常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'])val_dataset = datasets.ImageFolder(root=os.path.join(image_path, 'val'), transform=data_transform['val'])train_num = len(train_dataset)val_num = len(val_dataset)# write class_dict into json fileflower_list = train_dataset.class_to_idxclass_dict = dict((v, k) for k, v in flower_list.items())json_str = json.dumps(class_dict)with open('class_indices.json', 'w') as file:file.write(json_str)batch_size = 32train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=0)val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=4, shuffle=False, num_workers=0)net = AlexNet(num_classes=5)net.to(device)loss_function = nn.CrossEntropyLoss()optimizer = optim.Adam(net.parameters(), lr=0.0002)epochs = 5save_path = './model/AlexNet.pth'best_acc = 0.0train_steps = len(train_loader)  # train_num / batch_sizetrain_bar = tqdm(train_loader)val_bar = tqdm(val_loader)for epoch in range(epochs):# trainnet.train()epoch_loss = 0.0# 加入进度条train_bar = tqdm(train_loader)for step, data in enumerate(train_bar):images, labels = dataoptimizer.zero_grad()outputs = net(images.to(device))loss = loss_function(outputs, labels.to(device))loss.backward()optimizer.step()  # update x by optimizer# print statisticsepoch_loss += loss.item()train_bar.desc = 'train eporch[{}/{}] loss:{:.3f}'.format(epoch + 1, epochs, loss)# validatenet.eval()acc = 0.0with torch.no_grad():val_bar = tqdm(val_loader)for val_data in val_bar:val_images, val_labels = val_dataoutputs = net(val_images.to(device))predict_y = torch.max(outputs, dim=1)[1]  # [1]取每行最大值的索引acc += torch.eq(predict_y, val_labels.to(device)).sum().item()val_acc = acc / val_numprint('[epoch %d] train_loss: %.3f val_accuracy: %.3f' % (epoch + 1, epoch_loss / train_steps, val_acc))# find best accuracyif val_acc > best_acc:best_acc = val_acctorch.save(net.state_dict(), save_path)print('Train finished!')if __name__ == '__main__':main()

class_indices.json

{"0": "daisy", "1": "dandelion", "2": "roses", "3": "sunflowers", "4": "tulips"}

predict.py 

import os
import torch
from torchvision import transforms
from PIL import Image
import matplotlib.pyplot as plt
import json
from model import AlexNetdef main():device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')transform = transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# load imageimg_path = './2.jpg'assert os.path.exists(img_path), "file:'{}' does not exist".format(img_path)img = Image.open(img_path)plt.imshow(img)# input [N,C,H,W]img = transform(img)img = torch.unsqueeze(img, dim=0)# read class_indicesjson_path = './class_indices.json'assert os.path.exists(json_path), "file:'{}' does not exist".format(json_path)with open(json_path, 'r') as file:class_dict = json.load(file)  # {'0': 'daisy', '1': 'dandelion', '2': 'roses', '3': 'sunflowers', '4': 'tulips'}# load modelnet = AlexNet(num_classes=5).to(device)# load model weightsweight_path = './model/AlexNet.pth'assert os.path.exists(weight_path), "file:'{}' does not exist".format(weight_path)net.load_state_dict(torch.load(weight_path))# predictnet.eval()with torch.no_grad():output = torch.squeeze(net(img.to(device))).cpu()predict = torch.softmax(output, dim=0)predict_class = torch.argmax(predict).numpy()print_res = 'class:{} probability:{:.3}'.format(class_dict[str(predict_class)], predict[predict_class].numpy())plt.title(print_res)plt.show()for i in range(len(predict)):print('class:{:10} probability:{:.3}'.format(class_dict[str(i)], predict[i]))if __name__ == '__main__':main()

Result: