一、前期准备
1.设置GPU
import torch from torch import nn import torchvision from torchvision import transforms,datasets,models import matplotlib.pyplot as plt import os,PIL,pathlib
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") device
device(type='cuda')
2.导入数据
data_dir = './weather_photos/' data_dir = pathlib.Path(data_dir) data_paths = list(data_dir.glob('*')) classNames = [str(path).split('\\')[1] for path in data_paths] classNames
['cloudy', 'rain', 'shine', 'sunrise']
train_transforms = transforms.Compose([ transforms.Resize([224,224]),# resize输入图片 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensor transforms.Normalize( mean = [0.485, 0.456, 0.406], std = [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到 ]) test_transforms = transforms.Compose([ transforms.Resize([224,224]),# resize输入图片 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensor transforms.Normalize( mean = [0.485, 0.456, 0.406], std = [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到 ]) total_data = datasets.ImageFolder(data_dir,transform=train_transforms) total_data
Dataset ImageFolder Number of datapoints: 1125 Root location: weather_photos StandardTransform Transform: Compose( Resize(size=[224, 224], interpolation=PIL.Image.BILINEAR) ToTensor() Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) )
total_data.class_to_idx
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
3.划分数据集
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 0x1e42b97f4f0>,
<torch.utils.data.dataset.Subset at 0x1e42b196a30>)
batch_size = 4 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) break
Shape of X [N, C, H, W]: torch.Size([4, 3, 224, 224])
Shape of y: torch.Size([4])
二、搭建包含C3模块的模型
1.搭建模型
import torch.nn.functional as F def autopad(k, p=None): # kernel, padding # Pad to 'same' if p is None: p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad return p class Conv(nn.Module): # Standard convolution def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups super().__init__() self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False) self.bn = nn.BatchNorm2d(c2) self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity()) def forward(self, x): return self.act(self.bn(self.conv(x))) class Bottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 def forward(self, x): return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) class C3(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) def forward(self, x): return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1)) class model_K(nn.Module): def __init__(self): super(model_K, self).__init__() # 卷积模块 self.Conv = Conv(3, 32, 3, 2) # C3模块1 self.C3_1 = C3(32, 64, 3, 2) # 全连接网络层，用于分类 self.classifier = nn.Sequential( nn.Linear(in_features=802816, out_features=100), nn.ReLU(), nn.Linear(in_features=100, out_features=4) ) def forward(self, x): x = self.Conv(x) x = self.C3_1(x) x = torch.flatten(x, start_dim=1) x = self.classifier(x) return x device = "cuda" if torch.cuda.is_available() else "cpu" print("Using {} device".format(device)) model = model_K().to(device) model
Using cuda device Out[9]: model_K( (Conv): Conv( (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (C3_1): C3( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv3): Conv( (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (m): Sequential( (0): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) (1): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) (2): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) ) ) (classifier): Sequential( (0): Linear(in_features=802816, out_features=100, bias=True) (1): ReLU() (2): Linear(in_features=100, out_features=4, bias=True) ) )
2.查看模型详情
import torchsummary as summary summary.summary(model,(3,224,224))
0 Conv2d-9 [-1, 32, 112, 112] 1,024 BatchNorm2d-10 [-1, 32, 112, 112] 64 SiLU-11 [-1, 32, 112, 112] 0 Conv-12 [-1, 32, 112, 112] 0 Conv2d-13 [-1, 32, 112, 112] 9,216 BatchNorm2d-14 [-1, 32, 112, 112] 64 SiLU-15 [-1, 32, 112, 112] 0 Conv-16 [-1, 32, 112, 112] 0 Bottleneck-17 [-1, 32, 112, 112] 0 Conv2d-18 [-1, 32, 112, 112] 1,024 BatchNorm2d-19 [-1, 32, 112, 112] 64 SiLU-20 [-1, 32, 112, 112] 0 Conv-21 [-1, 32, 112, 112] 0 Conv2d-22 [-1, 32, 112, 112] 9,216 BatchNorm2d-23 [-1, 32, 112, 112] 64 SiLU-24 [-1, 32, 112, 112] 0 Conv-25 [-1, 32, 112, 112] 0 Bottleneck-26 [-1, 32, 112, 112] 0 Conv2d-27 [-1, 32, 112, 112] 1,024 BatchNorm2d-28 [-1, 32, 112, 112] 64 SiLU-29 [-1, 32, 112, 112] 0 Conv-30 [-1, 32, 112, 112] 0 Conv2d-31 [-1, 32, 112, 112] 9,216 BatchNorm2d-32 [-1, 32, 112, 112] 64 SiLU-33 [-1, 32, 112, 112] 0 Conv-34 [-1, 32, 112, 112] 0 Bottleneck-35 [-1, 32, 112, 112] 0 Conv2d-36 [-1, 32, 112, 112] 1,024 BatchNorm2d-37 [-1, 32, 112, 112] 64 SiLU-38 [-1, 32, 112, 112] 0 Conv-39 [-1, 32, 112, 112] 0 Conv2d-40 [-1, 64, 112, 112] 4,096 BatchNorm2d-41 [-1, 64, 112, 112] 128 SiLU-42 [-1, 64, 112, 112] 0 Conv-43 [-1, 64, 112, 112] 0 C3-44 [-1, 64, 112, 112] 0 Linear-45 [-1, 100] 80,281,700 ReLU-46 [-1, 100] 0 Linear-47 [-1, 4] 404 ================================================================ Total params: 80,320,536 Trainable params: 80,320,536 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 150.06 Params size (MB): 306.40 Estimated Total Size (MB): 457.04 ---------------------------------------------------------------
三、训练模型
1.编写训练函数
# 训练循环 def train(dataloader, model, loss_fn, optimizer): size = len(dataloader.dataset) # 训练集的大小，一共900张图片 num_batches = len(dataloader) # 批次数目，29（900/32） train_loss, train_acc = 0, 0 # 初始化训练损失和正确率 for X, y in dataloader: # 获取图片及其标签 X, y = X.to(device), y.to(device) # 计算预测误差 pred = model(X) # 网络输出 loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失 # 反向传播 optimizer.zero_grad() # grad属性归零 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
2.编写测试函数
def test (dataloader, model, loss_fn): size = len(dataloader.dataset) # 测试集的大小，一共10000张图片 num_batches = len(dataloader) # 批次数目，8（255/32=8，向上取整） test_loss, test_acc = 0, 0 # 当不进行训练时，停止梯度更新，节省计算内存消耗 with torch.no_grad(): for imgs, target in dataloader: imgs, target = imgs.to(device), target.to(device) # 计算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
3、正式训练
import copy optimizer = torch.optim.Adam(model.parameters(),lr=1e-4) # scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.92)#学习率每5个epoch衰减成原来的1/10 loss_fn = nn.CrossEntropyLoss() epochs = 20 train_loss = [] train_acc = [] test_loss = [] test_acc = [] best_acc = 0 for epoch in range(epochs): model.train() epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer) # scheduler.step()#学习率衰减 model.eval() epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn) # 保存最优模型 if epoch_test_acc > best_acc: best_acc = epoch_train_acc best_model = copy.deepcopy(model) train_acc.append(epoch_train_acc) train_loss.append(epoch_train_loss) test_acc.append(epoch_test_acc) test_loss.append(epoch_test_loss) # 获取当前学习率 lr = optimizer.state_dict()['param_groups'][0]['lr'] template = ('Epoch:{:2d}, Train_acc:{:.1f}%， Train_loss:{:.3f}， Test_acc:{:.1f}%，Test_loss:{:.3f}，Lr:{:.2E}') print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr)) # 保存最佳模型 PATH = './best_model.pth' torch.save(model.state_dict(),PATH) print('Done') print('best_acc：',best_acc)1.
Epoch:18, Train_acc:99.1%， Train_loss:0.043， Test_acc:84.9%，Test_loss:1.605，Lr:1.00E-04
Epoch:19, Train_acc:99.8%， Train_loss:0.009， Test_acc:89.8%，Test_loss:1.085，Lr:1.00E-04
Epoch:20, Train_acc:99.4%， Train_loss:0.014， Test_acc:89.3%，Test_loss:1.053，Lr:1.00E-04
Done
best_acc： 0.9666666666666667
四、结果可视化
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'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 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()
2.模型评估
best_model.eval() epoch_test_acc,epoch_test_loss = test(test_dl,best_model,loss_fn)
epoch_test_acc,epoch_test_loss
(0.8844444444444445, 1.0431718131294474)
1. # 查看是否与我们最高准确率一致 2. epoch_test_acc
0.8844444444444445
