一 前期工作
环境：python3.6，1080ti，pytorch1.10（实验室服务器的环境??）
1.设置GPU或者cpu
import torchimport torch.nn as nnimport matplotlib.pyplot as pltimport torchvision device = torch.device("cuda" if torch.cuda.is_available() else "cpu") device
2.导入数据
import os,PIL,random,pathlib data_dir = 'weather_photos/'data_dir = pathlib.Path(data_dir)print(data_dir) data_paths = list(data_dir.glob('*'))print(data_paths)classeNames = [str(path).split("/")[1] for path in data_paths]classeNames
二 数据预处理
数据格式设置
total_datadir = 'weather_photos/' # 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863train_transforms = transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 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-->转换为标准正太分布（高斯分布），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] 从数据集中随机抽样计算得到的。]) total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)total_data
数据集划分
train_size = int(0.8 * len(total_data))test_size = len(total_data) - train_sizetrain_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])train_dataset, test_dataset
设置dataset
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)
检查数据格式
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
三 搭建网络
import torchfrom torch import nnfrom torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential,ReLU num_classes = 4 class Model(nn.Module): def __init__(self): super(Model,self).__init__() # 卷积层 self.layers = Sequential( # 第一层 nn.Conv2d(3, 24, kernel_size=5), nn.BatchNorm2d(24), nn.ReLU(), # 第二层 nn.Conv2d(24,64 , kernel_size=5), nn.BatchNorm2d(64), nn.ReLU(), nn.MaxPool2d(2,2), nn.Conv2d(64, 128, kernel_size=5), nn.BatchNorm2d(128), nn.ReLU(), nn.Conv2d(128, 24, kernel_size=5), nn.BatchNorm2d(24), nn.ReLU(), nn.MaxPool2d(2,2), nn.Flatten(), nn.Linear(24*50*50, 516,bias=True), nn.ReLU(), nn.Dropout(0.5), nn.Linear(516, 215,bias=True), nn.ReLU(), nn.Dropout(0.5), nn.Linear(215, num_classes,bias=True), ) def forward(self, x): x = self.layers(x) return x device = "cuda" if torch.cuda.is_available() else "cpu"print("Using {} device".format(device)) model = Model().to(device)model
打印网络结构
四 训练模型1.设置学习率
loss_fn = nn.CrossEntropyLoss() # 创建损失函数learn_rate = 1e-3 # 学习率opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
2.模型训练
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60000张图片 num_batches = len(dataloader) # 批次数目，1875（60000/32） 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
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，313（10000/32=312.5，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
具体训练代码
epochs = 30train_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')
五 模型评估1.Loss和Accuracy图
import matplotlib.pyplot as plt#隐藏警告import warningswarnings.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.对结果进行预测
import osimport json import torchfrom PIL import Imagefrom torchvision import transformsimport matplotlib.pyplot as plt img_path = "weather_photos/cloudy/cloudy1.jpg"classes = ['cloudy', 'rain', 'shine', 'sunrise']data_transform = transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 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-->转换为标准正太分布（高斯分布），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] 从数据集中随机抽样计算得到的。])def main(): device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") img = Image.open(img_path) plt.imshow(img) # [N, C, H, W] img = data_transform(img) # expand batch dimension img = torch.unsqueeze(img, dim=0) model.eval() with torch.no_grad(): # predict class output = torch.squeeze(model(img.to(device))).cpu() predict = torch.softmax(output, dim=0) predict_cla = torch.argmax(predict).numpy() print(classes[predict_cla]) plt.show() if __name__ == '__main__': main()
预测结果如下：
3.总结
1.本次能主要对以下函数进行了学习
|
| ||
|
| ||
|
|