當前位置：首頁 > 编程资源 > 编程问答 >内容正文

编程问答

猫狗识别——PyTorch

發布時間：2025/4/16 编程问答 17 豆豆

生活随笔收集整理的這篇文章主要介紹了猫狗识别——PyTorch 小編覺得挺不錯的,現在分享給大家,幫大家做個參考.

貓狗識別

數據集下載：

　　網盤鏈接：https://pan.baidu.com/s/1SlNAPf3NbgPyf93XluM7Fg

　　提取密碼：hpn4

1. 要導入的包

import os import time import numpy as npimport torch import torch.nn as nn import torch.nn.functional as F from torch.utils.data import DataLoader from torch.utils import data from torchvision import transforms as T from PIL import Image import

2. 模型配置

################################### # SETTINGS ###################################class Config(object):batch_size = 32max_epoch = 30num_workers = 2lr = 0.001lr_decay = 0.95weight_decay = 0.0001train_data_root = '/home/dong/Documents/DATASET/train'test_data_root = '/home/dong/Documents/DATASET/test'load_dict_path = Noneopt = Config() SETTINGS

3. 選擇DEVICE

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

?4. 數據集

################################### # DATASETS ###################################class DogCatDataset(data.Dataset):def __init__(self, root, transforms=None, train=True, test=False):super(DogCatDataset, self).__init__()imgs = [os.path.join(root, img) for img in os.listdir(root)]np.random.seed(10000)np.random.permutation(imgs)len_imgs = len(imgs)self.test = test# -----------------------------------------------------------------------------------------# 因為在貓狗數據集中，只有訓練集和測試集，但是我們還需要驗證集，因此從原始訓練集中分離出30%的數據# 用作驗證集。# ------------------------------------------------------------------------------------------if self.test:self.imgs = imgselif train:self.imgs = imgs[: int(0.7*len_imgs)]else:self.imgs = imgs[int(0.7*len_imgs): ]if transforms is None:normalize = T.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])if self.test or not train:self.transforms = T.Compose([T.Scale(224),T.CenterCrop(224),T.ToTensor(),normalize])else:self.transforms = T.Compose([T.Scale(246),T.RandomCrop(224),T.RandomHorizontalFlip(),T.ToTensor(),normalize])def __getitem__(self, index):# 當前要獲取圖像的路徑img_path = self.imgs[index]if self.test:img_label = int(img_path.split('.')[-2].split('/')[-1])else:img_label = 1 if 'dog' in img_path.split('/')[-1] else 0img_data = Image.open(img_path)img_data = self.transforms(img_data)return img_data, img_labeldef __len__(self):return len(self.imgs)train_dataset = DogCatDataset(root=opt.train_data_root, train=True) # train=True, test=False -> 訓練集 val_dataset = DogCatDataset(root=opt.train_data_root, train=False) # train=False, test=False -> 驗證集 test_dataset = DogCatDataset(root=opt.test_data_root, test=True) # test=True -> 測試集 train_dataloader = DataLoader(dataset=train_dataset,shuffle=True,batch_size=opt.batch_size,num_workers = opt.num_workers) val_dataloader = DataLoader(dataset=val_dataset,shuffle=False,batch_size=opt.batch_size,num_workers = opt.num_workers) test_dataloader = DataLoader(dataset=test_dataset,shuffle=False,batch_size=opt.batch_size,num_workers = opt.num_workers) DATASETS

5. 檢查數據集的 shape

# ------------------------------------------------ # CHECKING THE DATASETS # ------------------------------------------------ print("Training set:") for images, labels in train_dataloader:print('Image Batch Dimensions:', images.size())print('Label Batch Dimensions:', labels.size())breakprint("Validation set:") for images, labels in val_dataloader:print('Image Batch Dimensions:', images.size())print('Label Batch Dimensions:', labels.size())breakprint("Testing set:") for images, labels in test_dataloader:print('Image Batch Dimensions:', images.size())print('Label Batch Dimensions:', labels.size())break View Code

eg:

Training set: Image Batch Dimensions: torch.Size([32, 3, 224, 224]) Label Batch Dimensions: torch.Size([32]) Validation set: Image Batch Dimensions: torch.Size([32, 3, 224, 224]) Label Batch Dimensions: torch.Size([32]) Testing set: Image Batch Dimensions: torch.Size([32, 3, 224, 224]) Label Batch Dimensions: torch.Size([32])

6. 模型定義

################################################### # MODEL ###################################################class AlexNet(nn.Module):def __init__(self, num_classes=2): # num_classes代表數據集的類別數 super(AlexNet, self).__init__()self.features = nn.Sequential(nn.Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=2),nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=(3, 3), stride=2),nn.Conv2d(64, 192, kernel_size=5, padding=2),nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2),nn.Conv2d(192, 384, kernel_size=3, padding=1),nn.ReLU(inplace=True),nn.Conv2d(384, 256, kernel_size=3, padding=1),nn.ReLU(inplace=True),nn.Conv2d(256, 256, kernel_size=3, padding=1),nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2))self.avgpool = nn.AdaptiveAvgPool2d((6, 6))self.classifers = nn.Sequential(nn.Dropout(),nn.Linear(256 * 6 * 6, 4096),nn.ReLU(inplace=True),nn.Dropout(),nn.Linear(4096, 4096),nn.ReLU(inplace=True),nn.Linear(4096, num_classes),)def forward(self, x):x = self.features(x)x = self.avgpool(x)x = x.view(x.size(0), 256*6*6)logits = self.classifers(x)probas = F.softmax(logits, dim=1)return logits, probas # 記載模型def load(self, model_path):self.load_state_dict(torch.load(model_path))# 保存模型def save(self, model_name):# 狀態字典的保存格式：文件名 + 日期時間 .pthprefix = 'checkpoints/' + model_name + '_'name = time.strftime(prefix + '%m%d_%H:%M:%S.pth')torch.save(self.state_dict, name)model = AlexNet() model = model.to(device) Model

7. 定義優化器

############################################## # Optimizer ############################################### optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) optimizer = torch.optim.SGD(model.parameters(), lr=opt.lr, momentum=0.8) Optimizer

8. 計算準確率

# ------------------------------------------- # 計算準確率 # ------------------------------------------- def compute_acc(model, dataloader, device):correct_pred, num_examples = 0, 0 # correct_pred 統計正確預測的樣本數，num_examples 統計樣本總數for i, (features, targets) in enumerate(dataloader):features = features.to(device)targets = targets.to(device)logits, probas = model(features)_, predicted_labels = torch.max(probas, 1)num_examples += targets.size(0)assert predicted_labels.size() == targets.size()correct_pred += (predicted_labels == targets).sum()return correct_pred.float() / num_examples * 100 compute_acc

9. 訓練 and 驗證

############################################## # TRAINING and VALIDATION ############################################## cost_list = [] train_acc_list, val_acc_list = [], []start_time = time.time()for epoch in range(opt.max_epoch):model.train()for batch_idx, (features, targets) in enumerate(train_dataloader):features = features.to(device)targets = targets.to(device)optimizer.zero_grad()logits, probas = model(features)# print(targets.size(), logits.size(), probas.size())cost = F.cross_entropy(logits, targets)# cost = torch.nn.CrossEntropyLoss(logits, targets) cost.backward()optimizer.step()cost_list.append(cost.item())if not batch_idx % 50:print('Epoch: %03d/%03d | Batch %03d/%03d | Cost: %.4f'%(epoch+1, opt.max_epoch, batch_idx, len(train_dataloader), cost))model.eval()with torch.set_grad_enabled(False): # save memory during inference train_acc = compute_acc(model, train_dataloader, device=device)val_acc = compute_acc(model, val_dataloader, device=device)print('Epoch: %03d/%03d | Training ACC: %.4f%% | Validation ACC: %.4f%%'%(epoch+1, opt.max_epoch, train_acc, val_acc))train_acc_list.append(train_acc)val_acc_list.append(val_acc)print('Time Elapsed: %.2f min' % ((time.time() - start_time)/60))print('Total Time Elapsed: %.2f min' % ((time.time() - start_time)/60)) Training and Validation

eg:

10. 可視化 Loss

plt.plot(cost_list, label='Minibatch cost') plt.plot(np.convolve(cost_list, np.ones(200,)/200, mode='valid'), label='Running average') plt.ylabel('Cross Entropy') plt.xlabel('Iteration') plt.legend() plt.show() visualize loss

eg:

11. 可視化準確率

plt.plot(np.arange(1, opt.max_epoch+1), train_acc_list, label='Training') plt.plot(np.arange(1, opt.max_epoch+1), val_acc_list, label='Validation')plt.xlabel('Epoch') plt.ylabel('Accuracy') plt.legend() plt.show() View Code

eg:

轉載于:https://www.cnblogs.com/xxxxxxxxx/p/11525583.html

總結

以上是生活随笔為你收集整理的猫狗识别——PyTorch的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。

上一篇： echarts - geo 绘制无数据区
下一篇： div拖拽的问题