chore: README contents

README.md

@@ -41,7 +41,7 @@ The CNN model consists of
 2. **Create virtual environment:**
    ```bash
    python -m venv .venv
-   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+   source .venv/bin/activate  # Windows: .venv\Scripts\activate
    ```
 
 3. **Install dependencies:**
@@ -50,6 +50,35 @@ The CNN model consists of
    ```
 
 
+## Model Code
+```py
+class CNN(nn.Module):
+    def __init__(self):
+        super(CNN, self).__init__()
+        self.conv1 = nn.Conv2d(3, 32, 3, stride=1, padding=1)  # 32x32 -> 16x16
+        self.bn1 = nn.BatchNorm2d(32)
+        self.conv2 = nn.Conv2d(32, 64, 3, stride=1, padding=1)  # 16x16 -> 8x8
+        self.bn2 = nn.BatchNorm2d(64)
+        self.conv3 = nn.Conv2d(64, 128, 3, stride=1, padding=1)  # 8x8 -> 4x4
+        self.bn3 = nn.BatchNorm2d(128)
+        self.pool = nn.MaxPool2d(stride=2, kernel_size=2)
+        self.fc1 = nn.Linear(128 * 4 * 4, 512)
+        self.fc2 = nn.Linear(512, 10)
+        self.dropout = nn.Dropout(0.5)
+
+    def forward(self, x):
+        x = self.pool(F.relu(self.bn1(self.conv1(x))))
+        x = self.pool(F.relu(self.bn2(self.conv2(x))))
+        x = self.pool(F.relu(self.bn3(self.conv3(x))))
+        x = x.view(x.size(0), -1)
+        x = self.dropout(x)
+        x = F.relu(self.fc1(x))
+        x = self.dropout(x)
+        x = self.fc2(x)
+        return x
+```
+
+
 ## Training Configuration
 
 - **Optimizer**: Adam (lr=0.001)
@@ -59,15 +88,18 @@ The CNN model consists of
 > Best model checkpoint was saved at epoch 49 with validation loss of 0.6553.
 
 
-## Performance
-
-![Training Loss](assets/loss.png)
-Reaching 0.7227 in Train loss and 0.6557 in Validation loss at epoch 50
+# Model
+There are two CNN models in `cnn/` folder
+- `model.pt`
+- `model-old.pt`
 
+`model.pt` was trained with `BatchNorm2d` to reach 81.45% accuracy in CIFAR-10 dataset
+`model-old.pt` was trained without fine tuning which gets 75% accuracy in CIFAR-10 dataset
 
 ### Accuracy:
 
 Total Accuracy: `81.45%`
+
 - **Airplane**: `84.60%`
 - **Automobile**: `93.20%`
 - **Bird**: `76.90%`