Update exp_recognition.py

app/Hackathon_setup/exp_recognition.py

@@ -8,6 +8,7 @@ from PIL import Image
 import base64
 import io
 import os
+import pdb
 ## Add more imports if required
 
 #############################################################################################################################
@@ -61,13 +62,15 @@ def get_expression(img):
     ##the same path as this file, we recommend to put in the same directory                 ##
     ##########################################################################################
     ##########################################################################################
-    face_det_net = facExpRec()
-    model = torch.load(current_path + '/exp_recognition_net.t7', map_location=device)
+   
+    face_det_net = facExpRec()                                         
+    model = torch.load(current_path + '/face_expression.t7', map_location=device)    
     face_det_net.load_state_dict(model['net_dict'])
     face = detected_face(img)
-    if face==0:
-        face = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2GRAY))
 
+    if face == 0:
+        face = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2GRAY))
+   
     with torch.no_grad():
         face = trnscm(face)
         output = face_det_net(face)
@@ -75,7 +78,7 @@ def get_expression(img):
 
     predicted_expression = classes[predicted.item()]
 
+    
     # YOUR CODE HERE, return expression using your model
 
-    return predicted_expression
-    
+    return predicted_expression

app/Hackathon_setup/exp_recognition_model.py

@@ -6,8 +6,8 @@ import torch.nn.functional as F
 ## Add more imports if required
 
 ####################################################################################################################
-# Define your model and transform and all necessary helper functions here                                          #
-# They will be imported to the exp_recognition.py file                                                             #
+# Define your model and transform and all necessary helper functions here #
+# They will be imported to the exp_recognition.py file #
 ####################################################################################################################
 
 # Definition of classes as dictionary
@@ -18,44 +18,32 @@ class facExpRec(torch.nn.Module):
     def __init__(self):
         super(facExpRec, self).__init__()
         self.conv1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=3)
-
         self.conv2 = nn.Conv2d(in_channels=16, out_channels=64, kernel_size=3)
-
         self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3)
-
-        # Define the Fully connected layers
-        # The output of the second convolution layer will be input to the first fully connected layer
-        self.fc1 = nn.Linear(128 * 10 * 10, 256)
-        # 256 input features, 128 output features
+        self.conv4 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=1)  
+        self.conv5 = nn.Conv2d(in_channels=256, out_channels=512, kernel_size=1)  
+        self.conv6 = nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=1) 
+        self.fc1 = nn.Linear(1024 * 1 * 1, 256)  
         self.fc2 = nn.Linear(256, 128)
-        # 128 input features, 64 output features
         self.fc3 = nn.Linear(128, 64)
-        # 64 input features, 7 output features for our 7 defined classes
         self.fc4 = nn.Linear(64, 7)
 
-        # Max pooling
-        self.pool = nn.MaxPool2d(kernel_size=2)  # Max pooling layer with filter size 2x2
-
+        self.pool = nn.MaxPool2d(kernel_size=2)
 
     def forward(self, x):
-        x = self.pool(F.relu(self.conv1(x)))
-        x = self.pool(F.relu(self.conv2(x)))
-        x = self.pool(F.relu(self.conv3(x)))
-        # Flatten the image
-        x = x.view(-1, 128 * 10 * 10)  # Output shape of convolutional layer is 16*5*5
-
-        # Linear layers with RELU activation
-        x = F.relu(self.fc1(x))
-        x = F.relu(self.fc2(x))
-        x = F.relu(self.fc3(x))
+        x = self.pool(F.elu(self.conv1(x)))
+        x = self.pool(F.elu(self.conv2(x)))
+        x = self.pool(F.elu(self.conv3(x)))
+        x = self.pool(F.elu(self.conv4(x)))  
+        x = self.pool(F.elu(self.conv5(x))) 
+        x = self.pool(F.elu(self.conv6(x)))  
+        x = x.view(-1, 1024 * 1 * 1)  
+        x = F.elu(self.fc1(x))
+        x = F.elu(self.fc2(x))
+        x = F.elu(self.fc3(x))
         x = self.fc4(x)
         x = F.log_softmax(x, dim=1)
         return x
-
-
-
-# remove 'pass' once you have written your code
-        #YOUR CODE HERE
         
 # Sample Helper function
 def rgb2gray(image):
@@ -63,4 +51,4 @@ def rgb2gray(image):
     
 # Sample Transformation function
 #YOUR CODE HERE for changing the Transformation values.
-trnscm = transforms.Compose([rgb2gray, transforms.Resize((48,48)), transforms.ToTensor()])
+trnscm = transforms.Compose([rgb2gray, transforms.Resize((100,100)), transforms.ToTensor()])

app/Hackathon_setup/exp_recognition_net.t7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bdcc922b6a7eb0117e3c5da04e4ea074bb87b1d59f60ff99aeb9c33380a6b7
+oid sha256:8c9fd9f96e8fd42c67f0381ee4de320e0073f93877ac617bf1286356e262f99b
 size 13612996

app/Hackathon_setup/expression_model.t7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e259073cae1db728ace85d09969082ac6055d611269aa9f4e10de3245f63ee41
+size 13612942