18_WDI_CNN/readme.md

# 지능화 캡스톤 프로젝트 #1 - WDI-CNN
### *Wafer Map 데이터를 9종류의 Class로 분류하는 CNN 모델 만들기*


-----

### 논문
반도체 제조공정의 불균형 데이터셋에 대한 웨이퍼 불량 식별을 위한 심층 컨볼루션 신경망

* 번역본
https://gitea.pinblog.codes/attachments/9b2424f7-7e7d-4ad1-a368-86a523d67504

* 원본
https://gitea.pinblog.codes/attachments/9a31bb80-bc0a-4d5a-83b1-4ef0557456ad

-----

### Dataset
[Kaggle - WDI Data](https://www.kaggle.com/qingyi/wm811k-wafer-map/code)

-----

### 수행방법

* 위 논문을 참고하여 CNN 모델을 구현하고, 
  WDI Dataset을 학습하여 9개의 클래스로 분류한다.
  
  (Center, Donut, Edge-Loc, Edge-Ring, Loc, Near-full, none, Random, Scratch)

  https://gitea.pinblog.codes/CBNU/03_WDI_CNN/releases/tag/info

  # Model


```python
import torch
import torch.nn as nn
import torch.nn.functional as F

class CNN_WDI(nn.Module):
    def __init__(self, class_num=9):
        super(CNN_WDI, self).__init__()

        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=0)
        self.bn1 = nn.BatchNorm2d(16)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 16, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(16)

        self.conv3 = nn.Conv2d(16, 32, kernel_size=3, padding=1)
        self.bn3 = nn.BatchNorm2d(32)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.conv4 = nn.Conv2d(32, 32, kernel_size=3, padding=1)
        self.bn4 = nn.BatchNorm2d(32)

        self.conv5 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.bn5 = nn.BatchNorm2d(64)
        self.pool3 = nn.MaxPool2d(2, 2)
        self.conv6 = nn.Conv2d(64, 64, kernel_size=3, padding=1)
        self.bn6 = nn.BatchNorm2d(64)

        self.conv7 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
        self.bn7 = nn.BatchNorm2d(128)
        self.pool4 = nn.MaxPool2d(2, 2)
        self.conv8 = nn.Conv2d(128, 128, kernel_size=3, padding=1)
        self.bn8 = nn.BatchNorm2d(128)

        self.spatial_dropout = nn.Dropout2d(0.2)
        self.pool5 = nn.MaxPool2d(2, 2)

        self.fc1 = nn.Linear(4608, 512)
        self.fc2 = nn.Linear(512, class_num)

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))
        x = self.pool1(F.relu(self.bn2(self.conv2(x))))

        x = F.relu(self.bn3(self.conv3(x)))
        x = self.pool2(F.relu(self.bn4(self.conv4(x))))

        x = F.relu(self.bn5(self.conv5(x)))
        x = self.pool3(F.relu(self.bn6(self.conv6(x))))

        x = F.relu(self.bn7(self.conv7(x)))
        x = self.pool4(F.relu(self.bn8(self.conv8(x))))

        x = self.spatial_dropout(x)
        x = self.pool5(x)

        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)

        return F.softmax(x, dim=1)

cnn_wdi = CNN_WDI(class_num=9)

```

# Load Data


```python
from torchvision import transforms, datasets

# 데이터 전처리
rotation_angles = list(range(0, 361, 15))
rotation_transforms = [transforms.RandomRotation(degrees=(angle, angle), expand=False, center=None, fill=None) for angle in rotation_angles]

data_transforms = transforms.Compose([
    transforms.Pad(padding=224, fill=0, padding_mode='constant'),
    transforms.RandomHorizontalFlip(),
    transforms.RandomVerticalFlip(),
    transforms.RandomApply(rotation_transforms, p=1),
    transforms.CenterCrop((224, 224)),
    transforms.ToTensor(),
])

# ImageFolder를 사용하여 데이터셋 불러오기
train_dataset = datasets.ImageFolder(root='E:/wm_images/train/', transform=data_transforms)
val_dataset = datasets.ImageFolder(root='E:/wm_images/val/', transform=data_transforms)
test_dataset = datasets.ImageFolder(root='E:/wm_images/test/', transform=data_transforms)
```

# Settings


```python
import torch.optim as optim

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
cnn_wdi.to(device)
print(str(device) + ' loaded.')

# 손실 함수 및 최적화 알고리즘 설정
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(cnn_wdi.parameters(), lr=0.001)

# 배치사이즈
batch_size = 18063360 #112

# 학습 및 평가 실행
num_epochs = 100 #* 192
# num_epochs = 50

# Random sample size
train_max_images = 95
val_max_images = 25

```

    

# Train Function


```python
# 학습 함수 정의
def train(model, dataloader, criterion, optimizer, device):
    model.train()
    running_loss = 0.0
    running_corrects = 0

    for inputs, labels in dataloader:
        inputs = inputs.to(device)
        labels = labels.to(device)

        optimizer.zero_grad()

        outputs = model(inputs)
        _, preds = torch.max(outputs, 1)
        loss = criterion(outputs, labels)

        loss.backward()
        optimizer.step()

        running_loss += loss.item() * inputs.size(0)
        running_corrects += torch.sum(preds == labels.data)

    epoch_loss = running_loss / len(dataloader.dataset)
    epoch_acc = running_corrects.double() / len(dataloader.dataset)

    return epoch_loss, epoch_acc
```

# Evaluate Function


```python
# 평가 함수 정의
def evaluate(model, dataloader, criterion, device):
    model.eval()
    running_loss = 0.0
    running_corrects = 0

    with torch.no_grad():
        for inputs, labels in dataloader:
            inputs = inputs.to(device)
            labels = labels.to(device)

            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)
            loss = criterion(outputs, labels)

            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / len(dataloader.dataset)
        epoch_acc = running_corrects.double() / len(dataloader.dataset)

    return epoch_loss, epoch_acc
```

# Train


```python
# Train & Validation의 Loss, Acc 기록 파일
s_title = 'Epoch,\tTrain Loss,\tTrain Acc,\tVal Loss,\tVal Acc\n'
with open('output.txt', 'a') as file:
    file.write(s_title)
print(s_title)

for epoch in range(num_epochs + 1):
    # 무작위 샘플 추출
    train_indices = torch.randperm(len(train_dataset))[:train_max_images]
    train_random_subset = torch.utils.data.Subset(train_dataset, train_indices)
    train_loader = torch.utils.data.DataLoader(train_random_subset, batch_size=batch_size, shuffle=True, num_workers=4)
    
    val_indices = torch.randperm(len(val_dataset))[:val_max_images]
    val_random_subset = torch.utils.data.Subset(train_dataset, val_indices)
    val_loader = torch.utils.data.DataLoader(val_random_subset, batch_size=batch_size, shuffle=False, num_workers=4)

    # 학습 및 Validation 평가
    train_loss, train_acc = train(cnn_wdi, train_loader, criterion, optimizer, device)
    val_loss, val_acc = evaluate(cnn_wdi, val_loader, criterion, device)

    # 로그 기록
    s_output = f'{epoch + 1}/{num_epochs},\t{train_loss:.4f},\t{train_acc:.4f},\t{val_loss:.4f},\t{val_acc:.4f}\n'
    with open('output.txt', 'a') as file:
        file.write(s_output)
    print(s_output)

    if epoch % 10 == 0:
        # 모델 저장
        torch.save(cnn_wdi.state_dict(), 'CNN_WDI_' + str(epoch) + 'epoch.pth')

-----

### 평가방법

* 모델의 성능지표(Precision, Recall, Accuracy, F1-Score)를 혼동행렬(Confusion Metrix)로 구현한다.

-----

### 테스트 결과

[1차 테스트](https://gitea.pinblog.codes/CBNU/03_WDI_CNN/wiki/1%EC%B0%A8-%ED%85%8C%EC%8A%A4%ED%8A%B8_%EC%9B%90%EB%B3%B8-%EB%8D%B0%EC%9D%B4%ED%84%B0-%ED%95%99%EC%8A%B5)