Python機器學習之基於Pytorch實現貓狗分類

一、環境配置

安裝Anaconda

具體安裝過程,請點擊本文

配置Pytorch

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple torch
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple torchvision

二、數據集的準備

1.數據集的下載

kaggle網站的數據集下載地址:
https://www.kaggle.com/lizhensheng/-2000

2.數據集的分類

將下載的數據集進行解壓操作,然後進行分類
分類如下(每個文件夾下包括cats和dogs文件夾)

在這裡插入圖片描述 

三、貓狗分類的實例

導入相應的庫

# 導入庫
import torch.nn.functional as F
import torch.optim as optim
import torch
import torch.nn as nn
import torch.nn.parallel
 
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torchvision.transforms as transforms
import torchvision.datasets as datasets

設置超參數

# 設置超參數
#每次的個數
BATCH_SIZE = 20
#迭代次數
EPOCHS = 10
#采用cpu還是gpu進行計算
DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

圖像處理與圖像增強

# 數據預處理
 
transform = transforms.Compose([
    transforms.Resize(100),
    transforms.RandomVerticalFlip(),
    transforms.RandomCrop(50),
    transforms.RandomResizedCrop(150),
    transforms.ColorJitter(brightness=0.5, contrast=0.5, hue=0.5),
    transforms.ToTensor(),
    transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])

讀取數據集和導入數據

# 讀取數據
 
dataset_train = datasets.ImageFolder('E:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small\\train', transform)
 
print(dataset_train.imgs)
 
# 對應文件夾的label
 
print(dataset_train.class_to_idx)
 
dataset_test = datasets.ImageFolder('E:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small\\validation', transform)
 
# 對應文件夾的label
 
print(dataset_test.class_to_idx)
 
# 導入數據
 
train_loader = torch.utils.data.DataLoader(dataset_train, batch_size=BATCH_SIZE, shuffle=True)
 
test_loader = torch.utils.data.DataLoader(dataset_test, batch_size=BATCH_SIZE, shuffle=True)

定義網絡模型

# 定義網絡
class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3)
        self.max_pool1 = nn.MaxPool2d(2)
        self.conv2 = nn.Conv2d(32, 64, 3) 
        self.max_pool2 = nn.MaxPool2d(2) 
        self.conv3 = nn.Conv2d(64, 64, 3) 
        self.conv4 = nn.Conv2d(64, 64, 3) 
        self.max_pool3 = nn.MaxPool2d(2) 
        self.conv5 = nn.Conv2d(64, 128, 3) 
        self.conv6 = nn.Conv2d(128, 128, 3) 
        self.max_pool4 = nn.MaxPool2d(2) 
        self.fc1 = nn.Linear(4608, 512) 
        self.fc2 = nn.Linear(512, 1)
  
    def forward(self, x): 
        in_size = x.size(0) 
        x = self.conv1(x) 
        x = F.relu(x) 
        x = self.max_pool1(x) 
        x = self.conv2(x) 
        x = F.relu(x) 
        x = self.max_pool2(x) 
        x = self.conv3(x) 
        x = F.relu(x) 
        x = self.conv4(x) 
        x = F.relu(x) 
        x = self.max_pool3(x) 
        x = self.conv5(x) 
        x = F.relu(x) 
        x = self.conv6(x) 
        x = F.relu(x)
        x = self.max_pool4(x) 
        # 展開
        x = x.view(in_size, -1)
        x = self.fc1(x)
        x = F.relu(x) 
        x = self.fc2(x) 
        x = torch.sigmoid(x) 
        return x
 
modellr = 1e-4
 
# 實例化模型並且移動到GPU
 
model = ConvNet().to(DEVICE)
 
# 選擇簡單暴力的Adam優化器,學習率調低
 
optimizer = optim.Adam(model.parameters(), lr=modellr)

調整學習率

def adjust_learning_rate(optimizer, epoch):
 
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    modellrnew = modellr * (0.1 ** (epoch // 5)) 
    print("lr:",modellrnew) 
    for param_group in optimizer.param_groups: 
        param_group['lr'] = modellrnew

定義訓練過程

# 定義訓練過程
def train(model, device, train_loader, optimizer, epoch):
 
    model.train() 
    for batch_idx, (data, target) in enumerate(train_loader):
 
        data, target = data.to(device), target.to(device).float().unsqueeze(1)
 
        optimizer.zero_grad()
 
        output = model(data)
 
        # print(output)
 
        loss = F.binary_cross_entropy(output, target)
 
        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_loader.dataset),
 
                    100. * (batch_idx + 1) / len(train_loader), loss.item()))
# 定義測試過程
 
def val(model, device, test_loader):
 
    model.eval()
 
    test_loss = 0
 
    correct = 0
 
    with torch.no_grad():
 
        for data, target in test_loader:
 
            data, target = data.to(device), target.to(device).float().unsqueeze(1)
 
            output = model(data)
            # print(output)
            test_loss += F.binary_cross_entropy(output, target, reduction='mean').item()
            pred = torch.tensor([[1] if num[0] >= 0.5 else [0] for num in output]).to(device)
            correct += pred.eq(target.long()).sum().item()
 
        print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
            test_loss, correct, len(test_loader.dataset),
            100. * correct / len(test_loader.dataset)))

定義保存模型和訓練

# 訓練
for epoch in range(1, EPOCHS + 1):
 
    adjust_learning_rate(optimizer, epoch)
    train(model, DEVICE, train_loader, optimizer, epoch) 
    val(model, DEVICE, test_loader)
 
torch.save(model, 'E:\\Cat_And_Dog\\kaggle\\model.pth')

訓練結果

在這裡插入圖片描述 

四、實現分類預測測試

準備預測的圖片進行測試

from __future__ import print_function, division
from PIL import Image
 
from torchvision import transforms
import torch.nn.functional as F
 
import torch
import torch.nn as nn
import torch.nn.parallel
# 定義網絡
class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3)
        self.max_pool1 = nn.MaxPool2d(2)
        self.conv2 = nn.Conv2d(32, 64, 3)
        self.max_pool2 = nn.MaxPool2d(2)
        self.conv3 = nn.Conv2d(64, 64, 3)
        self.conv4 = nn.Conv2d(64, 64, 3)
        self.max_pool3 = nn.MaxPool2d(2)
        self.conv5 = nn.Conv2d(64, 128, 3)
        self.conv6 = nn.Conv2d(128, 128, 3)
        self.max_pool4 = nn.MaxPool2d(2)
        self.fc1 = nn.Linear(4608, 512)
        self.fc2 = nn.Linear(512, 1)
 
    def forward(self, x):
        in_size = x.size(0)
        x = self.conv1(x)
        x = F.relu(x)
        x = self.max_pool1(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = self.max_pool2(x)
        x = self.conv3(x)
        x = F.relu(x)
        x = self.conv4(x)
        x = F.relu(x)
        x = self.max_pool3(x)
        x = self.conv5(x)
        x = F.relu(x)
        x = self.conv6(x)
        x = F.relu(x)
        x = self.max_pool4(x)
        # 展開
        x = x.view(in_size, -1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        x = torch.sigmoid(x)
        return x
# 模型存儲路徑
model_save_path = 'E:\\Cat_And_Dog\\kaggle\\model.pth'
 
# ------------------------ 加載數據 --------------------------- #
# Data augmentation and normalization for training
# Just normalization for validation
# 定義預訓練變換
# 數據預處理
transform_test = transforms.Compose([
    transforms.Resize(100),
    transforms.RandomVerticalFlip(),
    transforms.RandomCrop(50),
    transforms.RandomResizedCrop(150),
    transforms.ColorJitter(brightness=0.5, contrast=0.5, hue=0.5),
    transforms.ToTensor(),
    transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
 
 
class_names = ['cat', 'dog']  # 這個順序很重要,要和訓練時候的類名順序一致
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
# ------------------------ 載入模型並且訓練 --------------------------- #
model = torch.load(model_save_path)
model.eval()
# print(model)
 
image_PIL = Image.open('E:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small\\test\\cats\\cat.1500.jpg')
#
image_tensor = transform_test(image_PIL)
# 以下語句等效於 image_tensor = torch.unsqueeze(image_tensor, 0)
image_tensor.unsqueeze_(0)
# 沒有這句話會報錯
image_tensor = image_tensor.to(device)
 
out = model(image_tensor)
pred = torch.tensor([[1] if num[0] >= 0.5 else [0] for num in out]).to(device)
print(class_names[pred])

預測結果

在這裡插入圖片描述
在這裡插入圖片描述

實際訓練的過程來看,整體看準確度不高。而經過測試發現,該模型隻能對於貓進行識別,對於狗則會誤判。

五、參考資料

實現貓狗分類

到此這篇關於Python機器學習之基於Pytorch實現貓狗分類的文章就介紹到這瞭,更多相關Pytorch實現貓狗分類內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet!