Update app/Hackathon_setup/exp_recognition_model.py

app/Hackathon_setup/exp_recognition_model.py

@@ -2,10 +2,6 @@ import torch
 import torchvision
 import torch.nn as nn
 from torchvision import transforms
-import transformers
-from transformers.utils import logging
-
-transformers.logging.set_verbosity_info()
 ## Add more imports if required
 
 ####################################################################################################################
@@ -19,48 +15,45 @@ classes = {0: 'ANGER', 1: 'DISGUST', 2: 'FEAR', 3: 'HAPPINESS', 4: 'NEUTRAL', 5:
 # Example Network
 class facExpRec(torch.nn.Module):
     def __init__(self, out_features=7):
-        super().__init__()
+    super().__init__()
 
-        self.conv1 = self.convlayer(in_channels=1, out_channels=64, kernel_size=3)
-        self.conv2 = self.convlayer(in_channels=64, out_channels=128, kernel_size=5)
-        self.conv3 = self.convlayer(in_channels=128, out_channels=512, kernel_size=3)
-        self.conv4 = self.convlayer(in_channels=512, out_channels=512, kernel_size=3, max_pool=1)
+    self.conv1 = self.convlayer(in_channels=1, out_channels=64, kernel_size=3)
+    self.conv2 = self.convlayer(in_channels=64, out_channels=128, kernel_size=5)
+    self.conv3 = self.convlayer(in_channels=128, out_channels=512, kernel_size=3)
+    self.conv4 = self.convlayer(in_channels=512, out_channels=512, kernel_size=3, max_pool=1)
 
-        self.fc1 = self.fclayer(512, 256)
-        self.fc2 = self.fclayer(256, 512)
-        self.fc3 = nn.Linear(512, out_features)
-    
-    def convlayer(self, in_channels, out_channels, kernel_size, max_pool=2):
-        return nn.Sequential(
-            nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=1),
-            nn.BatchNorm2d(out_channels),
-            nn.ReLU(),
-            nn.Dropout2d(),
-            nn.MaxPool2d(kernel_size=max_pool),
-        )
+    self.fc1 = self.fclayer(512, 256)
+    self.fc2 = self.fclayer(256, 512)
+    self.fc3 = nn.Linear(512, out_features)
+  
+  def convlayer(self, in_channels, out_channels, kernel_size, max_pool=2):
+    return nn.Sequential(
+        nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=1),
+        nn.BatchNorm2d(out_channels),
+        nn.ReLU(),
+        nn.Dropout2d(),
+        nn.MaxPool2d(kernel_size=max_pool),
+    )
 
-    def fclayer(self, in_features, out_features):
-        return nn.Sequential(
-            nn.Linear(in_features, out_features),
-            nn.BatchNorm1d(out_features),
-            nn.Dropout1d(0.4),
-            nn.ReLU(),
-        )
+  def fclayer(self, in_features, out_features):
+    return nn.Sequential(
+        nn.Linear(in_features, out_features),
+        nn.BatchNorm1d(out_features),
+        nn.Dropout1d(0.4),
+        nn.ReLU(),
+    )
 
-    
-    def forward(self, x):
-        logger.info(x.shape)
-        x = self.conv1(x)
-        x = self.conv2(x)
-        x = self.conv3(x)
-        x = self.conv4(x)
-        logger.info(x.shape)
-        x = x.view(-1, 512)
-        logger.info(x.shape)
-        x = self.fc1(x)
-        x = self.fc2(x)
-        x = self.fc3(x)
-        return x
+  
+  def forward(self, x):
+    x = self.conv1(x)
+    x = self.conv2(x)
+    x = self.conv3(x)
+    x = self.conv4(x)
+    x = x.view(-1, 512)
+    x = self.fc1(x)
+    x = self.fc2(x)
+    x = self.fc3(x)
+    return x
         
 # Sample Helper function
 def rgb2gray(image):