Upload

.gitignore

@@ -0,0 +1,4 @@
+dataset
+*.pth
+.vscode
+__pycache__

model.py

@@ -0,0 +1,80 @@
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class CNNv1(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.conv1 = nn.Conv2d(1, 16, 3, 1)
+        self.conv2 = nn.Conv2d(16, 32, 3, 1)
+        self.fc1 = nn.Linear(32 * 54 * 54, 128)
+        self.fc2 = nn.Linear(128, 2)
+
+    def forward(self, x):
+        x = F.relu(self.conv1(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.conv2(x))
+        x = F.max_pool2d(x, 2, 2)
+        x = x.view(-1, 32 * 54 * 54)
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x
+
+
+class CNNv2(nn.Module):
+    def __init__(self) -> None:
+        super().__init__()
+        self.conv1 = nn.Conv2d(1, 32, 3, 1)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.conv2 = nn.Conv2d(32, 64, 3, 1)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.conv3 = nn.Conv2d(64, 128, 3, 1)
+        self.bn3 = nn.BatchNorm2d(128)
+        self.fc1 = nn.Linear(128 * 26 * 26, 256)
+        self.dropout = nn.Dropout(0.5)
+        self.fc2 = nn.Linear(256, 2)
+
+    def forward(self, x):
+        x = F.relu(self.bn1(self.conv1(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.bn2(self.conv2(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.bn3(self.conv3(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = x.view(-1, 128 * 26 * 26)
+        x = F.relu(self.fc1(x))
+        x = self.dropout(x)
+        x = self.fc2(x)
+        return x
+
+
+class CNNv3(nn.Module):
+    def __init__(self) -> None:
+        super().__init__()
+        self.conv1 = nn.Conv2d(1, 32, 3, 1)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.conv2 = nn.Conv2d(32, 64, 3, 1)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.conv3 = nn.Conv2d(64, 128, 3, 1)
+        self.bn3 = nn.BatchNorm2d(128)
+        self.conv4 = nn.Conv2d(128, 256, 3, 1)
+        self.bn4 = nn.BatchNorm2d(256)
+        self.global_avg_pool = nn.AdaptiveAvgPool2d((1, 1))
+        self.fc1 = nn.Linear(256, 128)
+        self.dropout = nn.Dropout(0.5)
+        self.fc2 = nn.Linear(128, 2)
+
+    def forward(self, x):
+        x = F.relu(self.bn1(self.conv1(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.bn2(self.conv2(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.bn3(self.conv3(x)))
+        x = F.max_pool2d(x, 2, 2)
+        x = F.relu(self.bn4(self.conv4(x)))
+        x = self.global_avg_pool(x)
+        x = x.view(-1, 256)
+        x = F.relu(self.fc1(x))
+        x = self.dropout(x)
+        x = self.fc2(x)
+        return x

predict.py

@@ -0,0 +1,28 @@
+from sys import argv
+import torch
+from PIL import Image
+
+from preprocess import TRANSFORM
+from settings import MODEL_FILENAME, CLASSES, OurCNN
+
+if __name__ == "__main__":
+
+    if len(argv) < 2:
+        print("Usage: predict.py <path>")
+        exit(1)
+
+    model = OurCNN()
+    model.load_state_dict(torch.load(MODEL_FILENAME))
+
+    # Load the image
+    image = Image.open(argv[1])
+
+    # Preprocess the image
+    tensor: torch.Tensor = TRANSFORM(image)  # type: ignore
+
+    # get the prediction
+    with torch.no_grad():
+        output = model(tensor.unsqueeze(0))
+    _, predicted = torch.max(output, 1)
+
+    print(CLASSES[predicted])

preprocess.py

@@ -0,0 +1,13 @@
+from torchvision import transforms
+from settings import (
+    IMAGE_TARGET_SIZE,
+)
+
+
+TRANSFORM = transforms.Compose(
+    [
+        transforms.Resize((IMAGE_TARGET_SIZE, IMAGE_TARGET_SIZE)),
+        transforms.Grayscale(num_output_channels=1),
+        transforms.ToTensor(),
+    ]
+)