Update app.py

app.py

@@ -5,77 +5,68 @@ import torch.nn as nn
 import torchvision.transforms as transforms
 import torchvision.models as models
 import os
+import torch
 
 # Set device
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
-# Define available models and their corresponding file names
-model_paths = {
-    "ResNet-18": "best_model9.pth",
-    "MobileNetV3 Large": "best_model3_mobilenetv3_large.pth",
-    "MobileNetV3 Small": "best_model13_mobilenetv3_small.pth"
-}
-
-def initialize_model(model_name):
-    if model_name == "ResNet-18":
-        model = models.resnet18(weights=None)
-        num_ftrs = model.fc.in_features
-        model.fc = nn.Sequential(
-            nn.Dropout(p=0.5),
-            nn.Linear(num_ftrs, 2)
-        )
-    elif model_name == "MobileNetV3 Large":
-        model = models.mobilenet_v3_large(weights=None)
-        num_ftrs = model.classifier[-1].in_features
-        model.classifier[-1] = nn.Linear(num_ftrs, 2)
-    elif model_name == "MobileNetV3 Small":
-        model = models.mobilenet_v3_small(weights=None)
-        num_ftrs = model.classifier[3].in_features
-        model.classifier[3] = nn.Linear(num_ftrs, 2)
-    else:
-        raise ValueError("Invalid model name")
-    
-    return model
+# Load the main classifier (Detector_best_model.pth)
+main_model = models.resnet18(weights=None)  # Updated: weights=None
+num_ftrs = main_model.fc.in_features
+# main_model.fc = nn.Linear(num_ftrs, 2)  # 2 classes: AI-generated_Image, Real_Image
+main_model.fc = nn.Sequential(
+    nn.Dropout(p=0.5),  # Match the training architecture
+    nn.Linear(num_ftrs, 2)  # 2 classes: AI-generated Image, Real Image
+)
 
-def load_model(model_name):
-    model = initialize_model(model_name)
-    model_path = model_paths[model_name]
-    model.load_state_dict(torch.load(model_path, map_location=device))
-    model = model.to(device)
-    model.eval()
-    return model
+main_model.load_state_dict(torch.load('best_model9.pth', map_location=device, weights_only=True))  # Updated: weights_only=True
+main_model = main_model.to(device)
+main_model.eval()
 
+# Define class names for the classifier based on the Folder structure
 classes_name = ['AI-generated Image', 'Real Image']
 
-# Define preprocessing transformations
+def convert_to_rgb(image):
+    """
+    Converts 'P' mode images with transparency to 'RGBA', and then to 'RGB'.
+    This is to avoid transparency issues during model training.
+    """
+    if image.mode in ('P', 'RGBA'):
+        return image.convert('RGB')
+    return image
+
+# Define preprocessing transformations (same used during training)
 preprocess = transforms.Compose([
-    transforms.Lambda(lambda img: img.convert('RGB') if img.mode in ('P', 'RGBA') else img),
-    transforms.Resize((224, 224)),
+    transforms.Lambda(convert_to_rgb),
+    transforms.Resize((224, 224)),  # Resize here, no need for shape argument in gr.Image
     transforms.ToTensor(),
-    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  # ImageNet normalization
 ])
 
-def classify_image(image, model_name):
-    if image is None:
-        return "Please upload an image."
-    
-    model = load_model(model_name)
+def classify_image(image):
+    # Open the image using PIL
     image = Image.fromarray(image)
+    
+    # Preprocess the image
     input_image = preprocess(image).unsqueeze(0).to(device)
     
+    # Perform inference with the main classifier
     with torch.no_grad():
-        output = model(input_image)
+        output = main_model(input_image)
         probabilities = torch.nn.functional.softmax(output[0], dim=0)
         confidence, predicted_class = torch.max(probabilities, 0)
     
-    return f"Image is: {classes_name[predicted_class]} (Confidence: {confidence.item():.4f})"
+    # Main classifier result
+    main_prediction = classes_name[predicted_class]
+    main_confidence = confidence.item()
+    
+    return f"Image is : {main_prediction} (Confidence: {main_confidence:.4f})"
 
-# Gradio interface
-image_input = gr.Image(image_mode="RGB")
-model_choice = gr.Dropdown(choices=list(model_paths.keys()), label="Choose Model", value="ResNet-18")
+# Gradio interface (updated)
+image_input = gr.Image(image_mode="RGB")  # Removed shape argument
 output_text = gr.Textbox()
 
-gr.Interface(fn=classify_image, inputs=[image_input, model_choice], outputs=[output_text],
-             title="AI-Generated Image Detector",
-             description="Upload an image and choose a model to detect AI-generated images.",
+gr.Interface(fn=classify_image, inputs=image_input, outputs=[output_text], 
+             title="Detect AI-generated Image ",
+             description="Upload an image to Detected AI-generated Image .",
              theme="default").launch()