- 🍨 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、我的环境:
1.语言环境:Python 3.8
2.编译器:Pycharm
3.深度学习环境:
- torch==1.12.1+cu113
- torchvision==0.13.1+cu113
二、GPU设置:
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
三、导入数据:
- pathlib.Path函数将字符串类型的文件夹路径转换为pathlib.Path对象。
- glob()方法获取data_dir路径下的所有文件路径,并以列表形式存储在data_paths中。
- split()函数对data_paths中的每个文件路径执行分割操作,获得各个文件所属的类别名称,并存储在classeNames中。
- 打印classeNames列表,显示每个文件所属的类别名称
import os,PIL,random,pathlib
data_dir = './data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
print(classeNames)
运行结果:
['test', 'train']
四、数据可视化:
# 指定图像文件夹路径
image_folder = './data/test/adidas/'
# 获取文件夹中的所有图像文件
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(2, 4, 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)
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
# 显示图像
plt.tight_layout()
plt.show()
运行结果:
五、划分数据集
# 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.RandomHorizontalFlip(), # 随机水平翻转
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。
])
test_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。
])
train_dataset = datasets.ImageFolder("./data/train/",transform=train_transforms)
test_dataset = datasets.ImageFolder("./data/test/",transform=train_transforms)
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
运行结果:
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
六、构建简单的CNN网络
对于一般的CNN网络来说,都是由特征提取网络和分类网络构成,其中特征提取网络用于提取图片的特征,分类网络用于将图片进行分类。
- nn.Conv2d为卷积层,用于提取图片的特征,传入参数为输入channel,输出channel,池化核大小
网络结构图:
import torch.nn.functional as F
class CNN(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1=nn.Sequential(
nn.Conv2d(3, 12, kernel_size=5, padding=0), # 12*220*220
nn.BatchNorm2d(12),
nn.ReLU())
self.conv2=nn.Sequential(
nn.Conv2d(12, 12, kernel_size=5, padding=0), # 12*216*216
nn.BatchNorm2d(12),
nn.ReLU())
self.pool3=nn.Sequential(
nn.MaxPool2d(2)) # 12*108*108
self.conv4=nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5, padding=0), # 24*104*104
nn.BatchNorm2d(24),
nn.ReLU())
self.conv5=nn.Sequential(
nn.Conv2d(24, 24, kernel_size=5, padding=0), # 24*100*100
nn.BatchNorm2d(24),
nn.ReLU())
self.pool6=nn.Sequential(
nn.MaxPool2d(2)) # 24*50*50
self.dropout = nn.Sequential(
nn.Dropout(0.2))
self.fc=nn.Sequential(
nn.Linear(24*50*50, len(classeNames)))
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x) # 卷积-BN-激活
x = self.conv2(x) # 卷积-BN-激活
x = self.pool3(x) # 池化
x = self.conv4(x) # 卷积-BN-激活
x = self.conv5(x) # 卷积-BN-激活
x = self.pool6(x) # 池化
x = self.dropout(x)
x = x.view(batch_size, -1) # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50
x = self.fc(x)
return x
加载并打印模型
import torchsummary as summary
model = Model()
summary.summary(model, (3, 224, 224))
运行结果:
七、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
num_batches = len(dataloader) # 批次数目, (size/batch_size,向上取整)
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
八、测试函数
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size,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
九、模型训练
if __name__ == "__main__":
main()
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)
设置动态学习率
def adjust_learning_rate(optimizer, epoch, start_lr):
# 每 2 个epoch衰减到原来的 0.92
lr = start_lr * (0.92 ** (epoch // 2))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
learn_rate = 1e-4 # 初始学习率
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
def main():
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
model = CNN()
train_transforms, train_dataset = get_transforms_dataset("./data/train/")
learn_rate = 1e-4 # 初始学习率
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
classes = list(train_dataset.class_to_idx)
for epoch in range(epochs):
# 更新学习率(使用自定义学习率时使用)
adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = train(get_data_loader("./data/train/"), model, loss_fn, optimizer)
# scheduler.step() # 更新学习率(调用官方动态学习率接口时使用)
model.eval()
epoch_test_acc, epoch_test_loss = test(get_data_loader("./data/test/"), 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)
# 获取当前的学习率
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))
print('Done')
运行结果:
十、模型评估
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()
运行结果:
十一、预测
torch.squeeze():对数据的维度进行压缩,去掉维数为1的的维度。
torch.unsqueeze():对数据维度进行扩充。给指定位置加上维数为一的维度。
def predict_one_image(image_path, model, transform, classes):
test_img = Image.open(image_path).convert('RGB')
# plt.imshow(test_img) # 展示预测的图片
test_img = transform(test_img)
img = test_img.unsqueeze(0)
model.eval()
output = model(img)
_, pred = torch.max(output, 1)
pred_class = classes[pred]
print(f'预测结果是:{pred_class}')
predict_one_image("./data/test/adidas/10.jpg", model, train_transforms, classes)
运行结果:
预测结果是:adidas
十二、增加测试集accuracy
更改优化器:
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)
通过更改优化器,增加dropout层,测试集accuracy最高可达到86.8%。
运行结果:
十三、保存并加载模型
# 模型保存
PATH = './model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))
保存最佳模型:
best_acc = 0
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
十四、总结
本次基于深度学习的pytorch实现运动鞋识别项目总结如下:
1.学习设置动态学习率,在训练的不同阶段自动调整学习率的大小,以使模型在全局最优解附近更好地收敛;
2.通过更换优化器、增加dropout层,来增加测试集acc;
3.通过每轮训练测试集的准确率,找到最高的,保存最佳模型权重。