- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者:K同学啊 | 接辅导、项目定制
一、本周学习内容
1、本地读取并加载数据
2、测试集accuracy到达93%
二、前言
本次使用pytorch实现对天气的识别,标签分为四类:‘cloudy’,‘rain’,‘shine’,‘sunrise’。数据集下载地址:链接: link(提取码:hqij )。
三、电脑环境
电脑系统:macOS Monterey 12.7.4
语言环境:Python 3.8.0
编译器:Jupyter Notebook
深度学习环境:torch:2.2.1 torchvision:0.17.1
四、前期准备
1、导入相关依赖项,设置CPU
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
# 设置硬件设备,如果有GPU则使用,没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
2、导入数据并显示
data_dir = './data/' # 获取数据集路径
data_dir = pathlib.Path(data_dir) # 将文件夹的路径转换为pathlib.Path对象
data_paths = list(data_dir.glob('*')) # 获取data_dir路径下所有文件的路径,并以list形式储存在data_paths中
classeNames = [str(path).split("/")[1] for path in data_paths] # 如果你的操作系统使用Windows,那么应该使用 .split("\\")。
import matplotlib.pyplot as plt
from PIL import Image
# 指定图像文件夹路径
image_folder = './data/cloudy/'
# 获取文件夹中的所有图像文件
# os.listdir()可以列举当前路径里的所有文件,endswith(str)判断是不是以str结尾的文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
# 创建Matplotlib图像
fig, axes = plt.subplots(3, 8, figsize=(16, 6))
# 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
img_path = os.path.join(image_folder, img_file) # os.path.join()用于路径拼接文件路径
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
# 显示图像
# plt.tight_layout(),Matplotlib 会自动调整子图的位置和大小,以确保所有元素都清晰可见,且没有重叠。
plt.tight_layout()
plt.show()
运行结果:
图形变换操作:
total_datadir = './data/'
# 关于transforms.Compose的更多介绍可以参考:https://blog.csdn.net/qq_38251616/article/details/124878863
train_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,Normalize函数做的是将数据变换到了[-1,1]之间
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
3、划分数据集
train_size = int(0.8 * len(total_data)) # 900
test_size = len(total_data) - train_size # 225
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
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)
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
输出结果:
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224]) Shape of y:
torch.Size([32]) torch.int64
五、搭建简单的CNN网络
import torch.nn.functional as F
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
"""
nn.Conv2d()函数:
第一个参数(in_channels)是输入的channel数量
第二个参数(out_channels)是输出的channel数量
第三个参数(kernel_size)是卷积核大小
第四个参数(stride)是步长,默认为1
第五个参数(padding)是填充大小,默认为0
"""
self.conv1 = nn.Conv2d(in_channels=3, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(24)
self.conv2 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn2 = nn.BatchNorm2d(24)
self.pool1 = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(in_channels=24, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(12)
self.conv5 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn5 = nn.BatchNorm2d(12)
self.pool2 = nn.MaxPool2d(2,2)
self.fc1 = nn.Linear(12*50*50, len(classeNames))
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = F.relu(self.bn2(self.conv2(x)))
x = self.pool1(x)
x = F.relu(self.bn4(self.conv4(x)))
x = F.relu(self.bn5(self.conv5(x)))
x = self.pool2(x)
x = x.view(-1, 12*50*50)
x = self.fc1(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
model
nn.BatchNorm2d 是 PyTorch(一个流行的深度学习框架)中的一个模块,用于实现二维批量归一化(Batch Normalization)。批量归一化是深度学习中的一种技术,它可以使模型训练更加稳定,并且通常能够加速训练过程,提高模型的性能。通常,nn.BatchNorm2d 被添加到神经网络模型中,位于卷积层(如 nn.Conv2d)和激活函数(如 ReLU)之间。torch.nn.BatchNorm2d(num_features, eps=1e-05, momentum=0.1,
affine=True, track_running_stats=True, device=None, dtype=None) 。
num_features这个数值通常与上一层(在这里是 nn.Conv2d 卷积层)的输出特征图的数量相匹配。
打印输入维度的变化:
import torchinfo
from torchinfo import summary
summary(model, (3, 224, 224), batch_dim = 0, col_names = ("input_size", "output_size", "num_params"), verbose = 0)
结果:
六、训练模型
1、设置超参数
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
2、编写训练函数
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
num_batches = len(dataloader)
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
3、编写测试函数
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
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
4、正式训练
epochs = 20
train_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')
输出结果:
七、结果可视化
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')
总结:
- 路径转为pathlib.Path(path)对象。
- glob()函数获取所有文件。
- torch.utils.data.random_split()划分数据集。
- nn.BatchNorm2d()实现归一化提高模型的性能。