deleted unnecessary methods

app.py

@@ -10,42 +10,7 @@ from PIL import Image
 
 
 
-
-
-# Moving both Data and Model into GPU
-
-def get_default_device():
-    """Pick GPU if available, else CPU"""
-    if torch.cuda.is_available():
-        return torch.device('cuda')
-    else:
-        return torch.device('cpu')
-    
-def to_device(data, device):
-    """Move tensor(s) to chosen device"""
-    if isinstance(data, (list,tuple)):
-        return [to_device(x, device) for x in data]
-    return data.to(device, non_blocking=True)
-
-class DeviceDataLoader():
-    """Wrap a dataloader to move data to a device"""
-    def __init__(self, dl, device):
-        self.dl = dl
-        self.device = device
-        
-    def __iter__(self):
-        """Yield a batch of data after moving it to device"""
-        for b in self.dl: 
-            yield to_device(b, self.device)
-
-    def __len__(self):
-        """Number of batches"""
-        return len(self.dl)
-
-
-
 # Defining our Class for just prediction
-
 def accuracy(outputs, labels):
     _, preds = torch.max(outputs, dim=1)
     return torch.tensor(torch.sum(preds == labels).item() / len(preds))
@@ -69,13 +34,10 @@ class ImageClassificationBase(nn.Module):
 
 
 # Defining our finetuned Resnet50 Architecture with our Classification layer
-
 class IndianFoodModelResnet50(ImageClassificationBase):
     def __init__(self, num_classes, pretrained=True):
         super().__init__()
-        # Use a pretrained model
         self.network = models.resnet50(pretrained=pretrained)
-        # Replace last layer
         self.network.fc = nn.Linear(self.network.fc.in_features, num_classes)
 
     def forward(self, xb):
@@ -83,7 +45,7 @@ class IndianFoodModelResnet50(ImageClassificationBase):
 
 
 
-# for prediction
+# Prediction method
 @torch.no_grad()
 def evaluate(model, val_loader):
     model.eval()
@@ -92,7 +54,7 @@ def evaluate(model, val_loader):
 
 
 
-# initialising our model and moving it to GPU
+# Initialising our model and moving it to CPU
 classes = ['burger',  'butter_naan',  'chai',  'chapati',  'chole_bhature', 
            'dal_makhani',  'dhokla',  'fried_rice',  'idli',  'jalebi',  
            'kaathi_rolls',  'kadai_paneer',  'kulfi',  'masala_dosa',  'momos',
@@ -103,40 +65,37 @@ to_device(model, device);
 
 
 
-# loading the model
+# Loading the model
 ckp_path = 'indianFood-resnet50.pth'
 model.load_state_dict(torch.load(ckp_path, map_location=torch.device('cpu')))
 model.eval()
 
 
 
-# image preprocessing before prediction
+# Image preprocessing before prediction
 stats = ((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
 img_tfms = tt.Compose([tt.Resize((224, 224)),
                         tt.ToTensor(), 
                         tt.Normalize(*stats, inplace = True)])
 
 def predict_image(image, model):
-    # Convert to a batch of 1
     xb = to_device(image.unsqueeze(0), device)
-    # Get predictions from model
     yb = model(xb)
-    # Pick index with highest probability
     _, preds  = torch.max(yb, dim=1)
-    # Retrieve the class label
     return classes[preds[0].item()]
 
 
 
+# Function handling input, processing and output
 def classify_image(path):
     img = Image.open(path)
     img = img_tfms(img)
-    #img = img.permute(2, 0, 1)
     label = predict_image(img, model)
-
     return label
 
 
+
+# Defining gradio interface functions
 image = gr.inputs.Image(shape=(224, 224), type="filepath")
 label = gr.outputs.Label(num_top_classes=1)
 
@@ -149,7 +108,6 @@ gr.Interface(
     outputs=label, 
     examples = [["idli.jpg"], ["naan.jpg"]],
     theme = "huggingface",
-    layout = "horizontal",
     title = "DesiVisionNet: Desi Food Vision with ResNet",
     description = "This is a Gradio demo for multi-class image classification of Indian food amongst 20 classes. The DesiVisionNet achieved 90% accuracy on our test dataset, performing well for a relatively efficient model. See the GitHub project page for detailed information below. Here, we provide a demo for real-world food classification. To use it, simply upload your image, or click one of the examples to load them.",
     article = article