Pytorch自定義CNN網路實現貓狗分類詳解過程

2022-12-09 14:03:21

前言

資料集下載地址：

連結: https://pan.baidu.com/s/17aglKyKFvMvcug0xrOqJdQ?pwd=6i7m

Dogs vs. Cats(貓狗大戰)來源Kaggle上的一個競賽題，任務為給定一個資料集，設計一種演演算法中的貓狗圖片進行判別。

資料集包括25000張帶標籤的訓練集圖片，貓和狗各125000張，標籤都是以cat or dog命名的。影象為RGB格式jpg圖片，size不一樣。截圖如下：

一. 資料預處理

pytorch的資料預處理部分要寫成一個類，這個類繼承Dataset類，並必須要實現三個函數。

from torch.utils.data import DataLoader,Dataset
from torchvision import transforms as T
import matplotlib.pyplot as plt
import os
from PIL import Image
class DogCat(Dataset):
    def __init__(self, root, transforms=None, train=True):
        imgs = [os.path.join(root,img) for img in os.listdir(root)]
        imgs_num = len(imgs)
        if train:
            self.imgs = imgs[:int(0.7 * imgs_num)]
        else:
            self.imgs = imgs[int(0.3 * imgs_num):]
        if transforms is None:
            normalize = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
            self.transforms = T.Compose([
                    T.Resize(224),
                    T.CenterCrop(224),
                    T.ToTensor(),
                    normalize
            ])
        else:
            self.transforms = transforms
    def __getitem__(self, index):
        img_path = self.imgs[index]
        # dog label : 1           cat label : 0
        label = 1 if "dog" in img_path.split('/')[-1] else 0
        data = Image.open(img_path)
        data = self.transforms(data)
        return data,label
    def __len__(self):
        return len(self.imgs)

__init__為建構函式，我這裡用力定義資料路徑，資料集劃分，transforms。

__getitem__為迭代函數，用來return單個資料的data和label。

__len__返回資料集的長度。

二. 定義網路

在這個例子中，我們用一個簡單的4層折積，2層全連線，最後跟一個sigmoid輸出二分類的概率的CNN網路。

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F
class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3)
        self.conv2 = nn.Conv2d(32, 64, 3)
        self.conv3 = nn.Conv2d(64, 128, 3)
        self.conv4 = nn.Conv2d(128, 128, 3)
        self.max_pool = nn.MaxPool2d(2)
        self.relu = nn.ReLU()
        self.sigmoid = nn.Sigmoid()
        # 12*12 for size(224,224)    7*7 for size(150,150)
        self.fc1 = nn.Linear(128*12*12, 512)
        self.fc2 = nn.Linear(512, 1)
    def forward(self, x):
        in_size = x.size(0)
        x = self.conv1(x)
        x = self.relu(x)
        x = self.max_pool(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.max_pool(x)
        x = self.conv3(x)
        x = self.relu(x)
        x = self.max_pool(x)
        x = self.conv4(x)
        x = self.relu(x)
        x = self.max_pool(x)
        # 展開
        x = x.view(in_size, -1)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.sigmoid(x)
        return x

pytorch定義網路時，必須實現兩個函數，建構函式主要定義一些網路塊，forward函數實現前向推理過程。且在後續程式碼中，如果定義物件model: ConvNet和資料image，可以直接通過model(image)來呼叫froward函數（python真的很神奇，C++出身的我理解這些騷操作好難）

三. 訓練模型

資料準備好了，模型網路定義好了，下一步當然是訓練權重了。

import torch
import torch.nn as nn
from torch.utils.data import DataLoader,Dataset
from dataset import DogCat
from network import ConvNet
from draw import draw_acc,draw_loss
train_data_root = "/home/elvis/workfile/dataset/dataset_kaggledogvscat/train"
batch_size = 256
# 1. prepare dataset
train_data = DogCat(train_data_root, train=True)
val_data = DogCat(train_data_root, train=False)
train_dataloader = DataLoader(train_data,batch_size=batch_size,shuffle=True)
val_dataloader = DataLoader(val_data,batch_size=batch_size,shuffle=True)
# 2. load model
model = ConvNet()
if torch.cuda.is_available():
    model.cuda()
# 3. prepare super parameters
criterion = nn.BCELoss()
learning_rate = 1e-3
# optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9)
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 4. train
train_loss_epoch = []
train_acc_epoch = []
val_loss_epoch = []
val_acc_epoch = []
for epoch in range(1, 10):
    model.train()
    train_loss = 0;
    train_acc = 0;
    for batch_idx, (data, target) in enumerate(train_dataloader):
        if torch.cuda.is_available():
            data, target = data.cuda(), target.cuda().float().unsqueeze(-1)
        else:
            data, target = data, target.float().unsqueeze(-1)
        optimizer.zero_grad()
        output = model(data)
        # print(output)
        loss = criterion(output, target)
        train_loss += loss.item();
        pred = torch.tensor([[1] if num[0] >= 0.5 else [0] for num in output]).cuda();
        train_acc += pred.eq(target.long()).sum().item();
        loss.backward()
        optimizer.step()
        if(batch_idx+1)%10 == 0: 
            print('Train Epoch: {} [{}/{} ({:.0f}%)]tLoss: {:.6f}'.format(
                epoch, (batch_idx+1) * len(data), len(train_dataloader.dataset),
                100. * (batch_idx+1) / len(train_dataloader), loss.item()))
    train_loss_epoch.append(train_loss / len(train_dataloader));
    train_acc_epoch.append(train_acc / len(train_dataloader.dataset));
    print('nTrain set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)'.format(train_loss / len(train_dataloader), train_acc, len(train_dataloader.dataset),
                                                                                    100. * train_acc / len(train_dataloader.dataset)));
    # val
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for batch_idx, (data, target) in enumerate(val_dataloader):
            if torch.cuda.is_available():
                data, target = data.cuda(), target.cuda().float().unsqueeze(-1)
            else:
                data, target = data, target.float().unsqueeze(-1)
            output = model(data)
            # print(output)
            test_loss += criterion(output, target).item(); #每個批次平均，一個epoch裡所有批次求和
            pred = torch.tensor([[1] if num[0] >= 0.5 else [0] for num in output]).cuda()
            correct += pred.eq(target.long()).sum().item()
    print('Valid set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)n'.format(test_loss/len(val_dataloader), correct, len(val_dataloader.dataset),
                                                                                    100. * correct / len(val_dataloader.dataset)));
    val_loss_epoch.append(test_loss / len(val_dataloader));
    val_acc_epoch.append(correct / len(val_dataloader.dataset));
    # Save model
    val_acc_rate = correct / len(val_dataloader.dataset);
    save = True
    best = "best.pt"
    last = "last.pt"
    if save:
        # Save last, best and delete
        torch.save(model.state_dict(), last)
        if val_acc_rate == max(val_acc_epoch):
            torch.save(model.state_dict(), best)
            print("save epoch {} model".format(epoch))
# 5. drawing
draw_loss(train_loss_epoch, val_loss_epoch)
draw_acc(train_acc_epoch,val_acc_epoch)

第一步，準備資料。先用我們之前定義的DogCat類來載入資料，但這個類繼承自dataset，是載入一條資料的。如果要批次載入資料，還要用pytorch內部的另一個類DataLoader，然後在建構函式裡傳入batchsize就可以批次載入資料了。注意這裡的類物件實際是一個生成器，後續通過迴圈就可以一直批次的去取資料了。

第二步，定義模型物件，有用顯示卡就把模型放在顯示卡上，沒有的話就用cpu跑。

第三步，定義一些超引數。因為是二分類，網路最後一層為sigmoid輸出類別的概率值，所以選用二分類交叉熵損失函數。再設定一下學習率和優化器。

第四步，訓練n個epoch。在每一個epoch裡計算訓練集準去率，驗證集準確率，並儲存模型。

最後結果像這樣