365天深度学习训练营-第P7周：咖啡豆识别

• 🍨 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

 我的环境：

• 语言环境：Python3.11.2
• 编译器：PyCharm Community Edition 2022.3
• 深度学习环境：torch==2.0,torchvision==0.15.1 

 本次目标：

• 自己搭建vgg16模型

---

  一、前期准备

        将数据集导入。

import torch
import torch.nn as nn
from torchvision import transforms,datasets
from torchvision.models import vgg16
import PIL,pathlib
from torchinfo import summary
import matplotlib.pyplot as plt

data_path='F:\\49-data'
data_path=pathlib.Path(data_path)
data_paths = list(data_path.glob('*'))
classNames = [str(path).split('\\')[2] for path in data_paths]
print(classNames)

'''
['Dark', 'Green', 'Light', 'Medium']
'''

        处理数据并划分数据集。

train_transforms = transforms.Compose([
    transforms.Resize([224,224]),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485,0.456,0.406],
        std=[0.229,0.224,0.225]
    )
])

total_data =datasets.ImageFolder(data_path, transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)

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])
print(train_dataset,test_dataset)
print(train_size,test_size)

batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,batch_size=batch_size)

二、构建vgg16模型

class vgg16(nn.Module):
    def __init__(self):
        super(vgg16, self).__init__()
        self.block1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        self.block2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        self.block3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        self.block4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        self.block5 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        self.classifier = nn.Sequential(
            nn.Linear(in_features=512 * 7 * 7, out_features=4096),
            nn.ReLU(),
            nn.Linear(in_features=4096, out_features=4096),
            nn.ReLU(),
            nn.Linear(in_features=4096, out_features=4)
        )

    def forward(self, x):
        x = self.block1(x)
        x = self.block2(x)
        x = self.block3(x)
        x = self.block4(x)
        x = self.block5(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)

        return x

model = vgg16().to("cpu")
summary(model)

        通过构建并实例化vgg16类进行模型初始化。这里构建了多个卷积块，并使用forward方法进行数据在卷积块间的传播。

​

三、训练模型

        设置超参数。

loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-3
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)

        编写训练函数和测试函数。

def train(dataloader,model,loss_fn,optimizer):
    size = len(dataloader.dataset)
    num_batchs = len(dataloader)
    train_loss, train_acc = 0, 0
    for X,y in dataloader:
        pred=model(X)
        loss=loss_fn(pred,y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        train_acc+=(pred.argmax(1)==y).type(torch.float).sum().item()
        train_loss+=loss.item()
    train_acc /= size
    train_loss /= num_batchs

    return train_acc,train_loss

def test(dataloader,model,loss_fn):
    size=len(dataloader.dataset)
    num_batchs=len(dataloader)
    test_loss,test_acc=0,0

    with torch.no_grad():
        for imgs,target in dataloader:

            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_batchs

    return test_acc,test_loss

        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,epoch_train_loss,epoch_test_acc,epoch_test_loss))
print('Done')

​

四、结果可视化

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='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

五、指定图片进行预测 

classes = list(total_data.class_to_idx)
def predict_one_img(image_path, model, transform, classes):
    test_img = PIL.Image.open(image_path).convert('RGB')
    test_img=transform(test_img)
    img = test_img.to('cpu').unsqueeze(0)
    model.eval()
    output = model(img)
    x,pred = torch.max(output,1)
    pred_class=classes[pred]
    print(f'预测结果是{pred_class}')
predict_one_img(image_path='F:\\49-data\\49-data\\Dark\\dark (1).png',model=model,transform=train_transforms,classes=classes)

        保存模型参数

PATH = './model.pth'
torch.save(model.state_dict(),PATH)

model.load_state_dict(torch.load(PATH))