Pytorch实战 | 第4天：猴痘病识别

我的环境：

  • 言语环境：Python3.10.11
  • 编译器：Jupyter Notebook
  • 深度学习结构：Pytorch 2.0.1+cu118
  • 显卡（GPU）：NVIDIA GeForce RTX 4070

相关教程：

  • 编译器教程：【新手入门深度学习 | 1-2：编译器Jupyter Notebook】
  • 深度学习环境配置教程：【新手入门深度学习 | 1-1：配置深度学习环境】
  • 一个深度学习小白需求的一切资料我都放这儿了：【新手入门深度学习 | 目录】

主张你学习本文之前先看看下面这篇入门文章，以便你能够更好的理解本文： 新手入门深度学习 | 2-1：图画数据建模流程示例

强烈主张我们运用Jupyter Notebook编译器翻开源码，你接下来的操作将会非常便捷的！

  • 如果你是深度学习小白，阅览本文前主张先学习一下 《新手入门深度学习》
  • 如果你有必定根底，可是缺少实战经验，可通过 《深度学习100例》 补齐根底
  • 别的，我们正在通过 365天深度学习练习营 抱团学习，营内为我们提供体系的学习教案与专业的辅导、非常良好的学习气氛，欢迎你的参加

要求：

  1. 练习过程中保存作用最好的模型参数。
  2. 加载最佳模型参数辨认本地的一张图片。
  3. 调整网络结构使测验集accuracy到达88%（要点）。

拔高（可选）：

  1. 调整模型参数并调查测验集的准确率改变。
  2. 尝试设置动态学习率。
  3. 测验集accuracy到达90%。

一、 前期准备

1. 设置GPU

如果设备上支持GPU就运用GPU,否则运用CPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

device(type='cuda')

2. 导入数据

import os,PIL,random,pathlib
data_dir = './4-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames

['Monkeypox', 'Others']

total_datadir = './4-data/'
# 关于transforms.Compose的更多介绍能够参阅：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成一致尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太散布（高斯散布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据会集随机抽样核算得到的。
])
total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data

Dataset ImageFolder
    Number of datapoints: 2142
    Root location: ./4-data/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=None)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

total_data.class_to_idx

{'Monkeypox': 0, 'Others': 1}

3. 区分数据集

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset

(<torch.utils.data.dataset.Subset at 0x16dac6e3fd0>,
 <torch.utils.data.dataset.Subset at 0x16dac6e3e50>)

train_size,test_size

(1713, 429)

batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=1)

for X, y in test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

Shape of X [N, C, H, W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

二、构建简单的CNN网络

import torch.nn.functional as F
class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        """
        nn.Conv2d()函数：
        第一个参数（in_channels）是输入的channel数量
        第二个参数（out_channels）是输出的channel数量
        第三个参数（kernel_size）是卷积核巨细
        第四个参数（stride）是步长，默以为1
        第五个参数（padding）是填充巨细，默以为0
        """
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)
        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.fc1 = nn.Linear(24*50*50, len(classeNames))
    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))      
        x = F.relu(self.bn2(self.conv2(x)))     
        x = self.pool(x)                        
        x = F.relu(self.bn4(self.conv4(x)))     
        x = F.relu(self.bn5(self.conv5(x)))  
        x = self.pool(x)                        
        x = x.view(-1, 24*50*50)
        x = self.fc1(x)
        return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
model

Using cuda device
Network_bn(
  (conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (fc1): Linear(in_features=60000, out_features=2, bias=True)
)

三、 练习模型

1. 设置超参数

loss_fn    = nn.CrossEntropyLoss() # 创建丢失函数
learn_rate = 1e-4 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2. 编写练习函数

# 练习循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 练习集的巨细，一共60000张图片
    num_batches = len(dataloader)   # 批次数目，1875（60000/32）
    train_loss, train_acc = 0, 0  # 初始化练习丢失和正确率
    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)
        # 核算猜测差错
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 核算网络输出和实在值之间的差距，targets为实在值，核算二者差值即为丢失
        # 反向传播
        optimizer.zero_grad()  # grad特点归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
    train_acc  /= size
    train_loss /= num_batches
    return train_acc, train_loss

3. 编写测验函数

测验函数和练习函数大致相同，可是由于不进行梯度下降对网络权重进行更新，所以不需求传入优化器

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测验集的巨细，一共10000张图片
    num_batches = len(dataloader)          # 批次数目，313（10000/32=312.5，向上取整）
    test_loss, test_acc = 0, 0
    # 当不进行练习时，停止梯度更新，节约核算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            # 核算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()
    test_acc  /= size
    test_loss /= num_batches
    return test_acc, test_loss

4. 正式练习

epochs     = 20
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []
for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')

Epoch: 1, Train_acc:60.8%, Train_loss:0.655, Test_acc:60.6%，Test_loss:0.668
Epoch: 2, Train_acc:70.2%, Train_loss:0.575, Test_acc:72.7%，Test_loss:0.560
Epoch: 3, Train_acc:74.5%, Train_loss:0.527, Test_acc:71.3%，Test_loss:0.549
Epoch: 4, Train_acc:78.4%, Train_loss:0.483, Test_acc:73.4%，Test_loss:0.519
....
Epoch:18, Train_acc:91.4%, Train_loss:0.271, Test_acc:83.0%，Test_loss:0.382
Epoch:19, Train_acc:92.6%, Train_loss:0.260, Test_acc:83.7%，Test_loss:0.381
Epoch:20, Train_acc:92.1%, Train_loss:0.260, Test_acc:82.3%，Test_loss:0.396
Done

四、 成果可视化

1. Loss与Accuracy图

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显现中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显现负号
plt.rcParams['figure.dpi']         = 100        #分辨率
epochs_range = range(epochs)
plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

Pytorch实战 | 第4天：猴痘病识别

2. 指定图片进行猜测

⭐torch.squeeze()详解

对数据的维度进行压缩，去掉维数为1的的维度

函数原型：

torch.squeeze(input, dim=None, *, out=None)

要害参数阐明：

  • input (Tensor)：输入Tensor
  • dim (int, optional)：如果给定，输入将只在这个维度上被压缩

实战事例：

>>> x = torch.zeros(2, 1, 2, 1, 2)
>>> x.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x)
>>> y.size()
torch.Size([2, 2, 2])
>>> y = torch.squeeze(x, 0)
>>> y.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x, 1)
>>> y.size()
torch.Size([2, 2, 1, 2])

⭐torch.unsqueeze()

对数据维度进行扩大。给指定方位加上维数为一的维度

函数原型：

torch.unsqueeze(input, dim)

要害参数阐明：

  • input (Tensor)：输入Tensor
  • dim (int)：刺进单例维度的索引

实战事例：

>>> x = torch.tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
tensor([[ 1,  2,  3,  4]])
>>> torch.unsqueeze(x, 1)
tensor([[ 1],
        [ 2],
        [ 3],
        [ 4]])

from PIL import Image
classes = list(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
    test_img = Image.open(image_path).convert('RGB')
    # plt.imshow(test_img)  # 展示猜测的图片
    test_img = transform(test_img)
    img = test_img.to(device).unsqueeze(0)
    model.eval()
    output = model(img)
    _,pred = torch.max(output,1)
    pred_class = classes[pred]
    print(f'猜测成果是：{pred_class}')

# 猜测练习会集的某张照片
predict_one_image(image_path='./4-data/Monkeypox/M01_01_00.jpg', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)

猜测成果是：Monkeypox

五、保存并加载模型

# 模型保存
PATH = './model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)
# 将参数加载到model傍边
model.load_state_dict(torch.load(PATH, map_location=device))

<All keys matched successfully>