similarity

app/Hackathon_setup/face_recognition.py

@@ -73,6 +73,15 @@ def get_similarity(img1, img2):
     ##########################################################################################
     
     # YOUR CODE HERE, load the model
+    feature_net = SiameseNetwork()
+    model = torch.load(current_path + '/siamese_model.t7',map_location=torch.device('cpu'))
+    feature_net.load_state_dict(model['net_dict'])
+
+    # YOUR CODE HERE, return similarity measure using your model
+    # Extract features of images inputs_1 and inputs_2
+    features_1,features_2 = feature_net(face1,face2)
+
+    dissimilarity = torch.nn.functional.cosine_similarity(features_1, features_2).item()
     
     # YOUR CODE HERE, return similarity measure using your model
     

app/Hackathon_setup/face_recognition_model.py

@@ -13,13 +13,46 @@ 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 forward(self, x):
-        pass   # remove 'pass' once you have written your code
-        #YOUR CODE HERE
-        
+        super(SiameseNetwork, self).__init__()
+        self.cnn1 = nn.Sequential(
+            nn.ReflectionPad2d(1),       #Pads the input tensor using the reflection of the input boundary, it similar to the padding.
+            nn.Conv2d(1, 4, kernel_size=3),
+            nn.ReLU(inplace=True),
+            nn.BatchNorm2d(4),
+
+            nn.ReflectionPad2d(1),
+            nn.Conv2d(4, 8, kernel_size=3),
+            nn.ReLU(inplace=True),
+            nn.BatchNorm2d(8),
+
+
+            nn.ReflectionPad2d(1),
+            nn.Conv2d(8, 8, kernel_size=3),
+            nn.ReLU(inplace=True),
+            nn.BatchNorm2d(8),
+        )
+
+        self.fc1 = nn.Sequential(
+            nn.Linear(8*100*100, 500),
+            nn.ReLU(inplace=True),
+
+            nn.Linear(500, 500),
+            nn.ReLU(inplace=True),
+
+            nn.Linear(500, 5))
+
+    # forward_once is for one image. This can be used while classifying the face images
+    def forward_once(self, x):
+        output = self.cnn1(x)
+        output = output.view(output.size()[0], -1)
+        output = self.fc1(output)
+        return output
+
+    def forward(self, input1, input2):
+        output1 = self.forward_once(input1)
+        output2 = self.forward_once(input2)
+        return output1, output2
+
 ##########################################################################################################
 ## Sample classification network (Specify if you are using a pytorch classifier during the training)    ##
 ## classifier = nn.Sequential(nn.Linear(64, 64), nn.BatchNorm1d(64), nn.ReLU(), nn.Linear...)           ##
@@ -28,4 +61,4 @@ class Siamese(torch.nn.Module):
 # YOUR CODE HERE for pytorch classifier
 
 # Definition of classes as dictionary
-classes = ['person1','person2','person3','person4','person5','person6','person7']
+classes = ['person1','person2','person3','person4','person5','person6','person7']