Merge branch 'main' of https://github.com/icanSeeo/i-can-see into clean

.github/workflows/ci.yml

@@ -0,0 +1,42 @@
+# name: Python application
+
+# on:
+#   push:
+#     branches: [ "CI/CD" ]
+#   pull_request:
+#     branches: [ "CI/CD" ]
+
+# permissions:
+#   contents: read
+
+# jobs:
+#   build:
+
+#     runs-on: ubuntu-latest
+
+#     steps:
+#     - uses: actions/checkout@v3
+#     - name: Set up Python 3.10
+#       uses: actions/setup-python@v3
+#       with:
+#         python-version: "3.10"
+#     - name: Install dependencies
+#       run: |
+#         python -m pip install --upgrade pip
+#         pip install flake8 pytest
+#         pip install torch torchvision  
+#     - name: Lint with flake8
+#       run: |
+#         # stop the build if there are Python syntax errors or undefined names
+#         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+#         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+#         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+#     - name: Test with pytest
+#       run: |
+#         cd test  
+#         pytest -v  
+#     - name: Build Docker image
+#       run: docker build -t my-python-app .
+
+#     - name: Run tests in Docker container
+#       run: docker run my-python-app

Dockerfile

@@ -0,0 +1,5 @@
+FROM python:3.10
+WORKDIR /app
+COPY . /app
+RUN pip install --upgrade pip && pip install flake8 pytest torch torchvision
+CMD ["python", "-m", "pytest", "-v", "./test/test_resnet.py"]

README.md

@@ -1,2 +1,29 @@
-# i-can-see
-Attention based CNN
+# 🔍 i-can-see
+👁‍🗨 Attention based CNN
+
+## 📸 Index
+<details open="open">
+  <ol>
+    <li>  프로젝트 소개</li>
+    <li>  기술 스택</li>
+    <li>  팀원 정보</li>
+    <li>  Doc</li>
+  </ol>
+</details>
+
+## 🐧 프로젝트 소개  
+<ul>
+  <li>Attention 기반 CNN 활용한 이미지 Blur 및 Noise 완화</li>
+  <ul>
+    <li>Attention~!</li>
+  </ul>
+</ul>
+
+## Team Member
+> BigData Project
+
+| Name | Role | Contect |   
+|:---:|:---:|:---:| 
+|강성준| slave, 블록체인 개발자 | [email protected] |   
+|조준영| AI 개발자, 웹디자이너 | [email protected] |
+|김동현| slave, 백엔드 개발자 | [email protected] |

test/test.txt

@@ -0,0 +1,70 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision
+import torchvision.transforms as transforms
+
+def test_training():
+    # 데이터 전처리
+    transform = transforms.Compose([
+        transforms.Resize((32, 32)),
+        transforms.ToTensor(),
+        transforms.Normalize((0.1307,), (0.3081,))
+    ])
+
+    trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
+    trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
+
+    testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
+    testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)
+
+    # ResNet 모델 정의
+    resnet = torchvision.models.resnet18(pretrained=True)
+    resnet.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3)
+    num_ftrs = resnet.fc.in_features
+    resnet.fc = nn.Linear(num_ftrs, 10)
+
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+    resnet.to(device)
+
+    # 손실 함수 및 최적화 함수
+    criterion = nn.CrossEntropyLoss()
+    optimizer = optim.SGD(resnet.parameters(), lr=0.01)
+
+    # 모델 학습
+    num_epochs = 2
+
+    for epoch in range(num_epochs):
+        running_loss = 0.0
+        resnet.train()
+
+        for i, (inputs, labels) in enumerate(trainloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+
+            optimizer.zero_grad()
+
+            outputs = resnet(inputs)
+            loss = criterion(outputs, labels)
+
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+
+
+    correct = 0
+    total = 0
+    resnet.eval()
+
+    with torch.no_grad():
+        for data in testloader:
+            images, labels = data
+            images, labels = images.to(device), labels.to(device)
+            outputs = resnet(images)
+            _, predicted = torch.max(outputs.data, 1)
+            total += labels.size(0)  
+            correct += (predicted == labels).sum().item()
+
+
+    assert correct / total >= 0.1, f"Accuracy: {100 * correct / total}%"

test/test_resnet.py

@@ -0,0 +1,70 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision
+import torchvision.transforms as transforms
+
+def test_training():
+    # 데이터 전처리
+    transform = transforms.Compose([
+        transforms.Resize((32, 32)),
+        transforms.ToTensor(),
+        transforms.Normalize((0.1307,), (0.3081,))
+    ])
+
+    trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
+    trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
+
+    testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
+    testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)
+
+    # ResNet 모델 정의
+    resnet = torchvision.models.resnet18(pretrained=True)
+    resnet.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3)
+    num_ftrs = resnet.fc.in_features
+    resnet.fc = nn.Linear(num_ftrs, 10)
+
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+    resnet.to(device)
+
+    # 손실 함수 및 최적화 함수
+    criterion = nn.CrossEntropyLoss()
+    optimizer = optim.SGD(resnet.parameters(), lr=0.01)
+
+    # 모델 학습
+    num_epochs = 2
+
+    for epoch in range(num_epochs):
+        running_loss = 0.0
+        resnet.train()
+
+        for i, (inputs, labels) in enumerate(trainloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+
+            optimizer.zero_grad()
+
+            outputs = resnet(inputs)
+            loss = criterion(outputs, labels)
+
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+
+
+    correct = 0
+    total = 0
+    resnet.eval()
+
+    with torch.no_grad():
+        for data in testloader:
+            images, labels = data
+            images, labels = images.to(device), labels.to(device)
+            outputs = resnet(images)
+            _, predicted = torch.max(outputs.data, 1)
+            total += labels.size(0)  
+            correct += (predicted == labels).sum().item()
+
+
+    assert correct / total >= 0.1, f"Accuracy: {100 * correct / total}%"

test/test_training.py

@@ -0,0 +1,70 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision
+import torchvision.transforms as transforms
+
+def test_training():
+    # 데이터 전처리
+    transform = transforms.Compose([
+        transforms.Resize((32, 32)),
+        transforms.ToTensor(),
+        transforms.Normalize((0.1307,), (0.3081,))
+    ])
+
+    trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
+    trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
+
+    testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
+    testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)
+
+    # ResNet 모델 정의
+    resnet = torchvision.models.resnet18(pretrained=True)
+    resnet.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3)
+    num_ftrs = resnet.fc.in_features
+    resnet.fc = nn.Linear(num_ftrs, 10)
+
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+    resnet.to(device)
+
+    # 손실 함수 및 최적화 함수
+    criterion = nn.CrossEntropyLoss()
+    optimizer = optim.SGD(resnet.parameters(), lr=0.01)
+
+    # 모델 학습
+    num_epochs = 5
+
+    for epoch in range(num_epochs):
+        running_loss = 0.0
+        resnet.train()
+
+        for i, (inputs, labels) in enumerate(trainloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+
+            optimizer.zero_grad()
+
+            outputs = resnet(inputs)
+            loss = criterion(outputs, labels)
+
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+
+
+    correct = 0
+    total = 0
+    resnet.eval()
+
+    with torch.no_grad():
+        for data in testloader:
+            images, labels = data
+            images, labels = images.to(device), labels.to(device)
+            outputs = resnet(images)
+            _, predicted = torch.max(outputs.data, 1)
+            total += labels.size(0)
+            correct += (predicted == labels).sum().item()
+
+
+    assert correct / total >= 0.9, f"Accuracy: {100 * correct / total}%"