Update app/Hackathon_setup/face_recognition_model.py

app/Hackathon_setup/face_recognition_model.py

@@ -12,13 +12,56 @@ trnscm = transforms.Compose([transforms.Resize((100,100)), transforms.ToTensor()
 
 ##Example Network
 class Siamese(torch.nn.Module):
-    def __init__(self):
-        super(Siamese, self).__init__()
-        #YOUR CODE HERE
+    def _init_(self, embedding_dim=128):
+        super(Siamese, self)._init_()
+        # Convolutional layers for feature extraction
+        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)
+        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
+        self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
+        self.conv4 = nn.Conv2d(128, 256, kernel_size=3, padding=1)
         
-    def forward(self, x):
-        pass   # remove 'pass' once you have written your code
-        #YOUR CODE HERE
+        # Batch normalization layers
+        self.bn1 = nn.BatchNorm2d(32)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.bn3 = nn.BatchNorm2d(128)
+        self.bn4 = nn.BatchNorm2d(256)
+        
+        # Pooling layer
+        self.pool = nn.MaxPool2d(2, 2)
+        
+        # Fully connected layers for embedding
+        self.fc1 = nn.Linear(256 * 6 * 6, 512)  # 100x100 -> 6x6 after 4 pooling layers
+        self.fc2 = nn.Linear(512, embedding_dim)
+        
+        # Dropout for regularization
+        self.dropout = nn.Dropout(0.5)
+        
+    def forward_once(self, x):
+        """Forward pass for a single input (used for feature extraction)"""
+        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 = self.pool(F.relu(self.bn4(self.conv4(x))))
+        
+        # Flatten the feature maps
+        x = x.view(x.size(0), -1)
+        
+        # Fully connected layers
+        x = F.relu(self.fc1(x))
+        x = self.dropout(x)
+        x = self.fc2(x)
+        
+        # L2 normalize the embeddings for better cosine similarity
+        x = F.normalize(x, p=2, dim=1)
+        
+        return x
+        
+    def forward(self, x1, x2):
+        """Forward pass for siamese network (two inputs)"""
+        output1 = self.forward_once(x1)
+        output2 = self.forward_once(x2)
+        return output1, output2
+
         
 ##########################################################################################################
 ## Sample classification network (Specify if you are using a pytorch classifier during the training)    ##