Update app.py

app.py

@@ -106,12 +106,12 @@ class AttentionUNET(nn.Module):
         return self.final_conv(x)
 
 def download_model():
-    """Download your trained model from HuggingFace"""
+    """Download trained model from HuggingFace"""
     model_url = "https://huggingface.co/spaces/ArchCoder/the-op-segmenter/resolve/main/best_attention_model.pth.tar"
     model_path = "best_attention_model.pth.tar"
     
     if not os.path.exists(model_path):
-        print("Downloading your trained model...")
+        print("Downloading trained model...")
         try:
             urllib.request.urlretrieve(model_url, model_path)
             print("Model downloaded successfully!")
@@ -123,39 +123,39 @@ def download_model():
     
     return model_path
 
-def load_your_attention_model():
-    """Load YOUR trained Attention U-Net model"""
+def load_attention_model():
+    """Load trained Attention U-Net model"""
     global model
     if model is None:
         try:
-            print("Loading your trained Attention U-Net model...")
+            print("Loading trained Attention U-Net model...")
             
             # Download model if needed
             model_path = download_model()
             if model_path is None:
                 return None
             
-            # Initialize your model architecture
+            # Initialize model architecture
             model = AttentionUNET(in_channels=1, out_channels=1).to(device)
             
-            # Load your trained weights
+            # Load trained weights
             checkpoint = torch.load(model_path, map_location=device, weights_only=True)
             model.load_state_dict(checkpoint["state_dict"])
             model.eval()
             
-            print("Your Attention U-Net model loaded successfully!")
+            print("Attention U-Net model loaded successfully!")
         except Exception as e:
-            print(f"Error loading your model: {e}")
+            print(f"Error loading model: {e}")
             model = None
     return model
 
-def preprocess_for_your_model(image):
-    """Preprocessing exactly like your Colab code"""
-    # Convert to grayscale (like your Colab code)
+def preprocess_image(image):
+    """Preprocessing for model input"""
+    # Convert to grayscale
     if image.mode != 'L':
         image = image.convert('L')
     
-    # Use the exact same transform as your Colab code
+    # Apply transforms
     val_test_transform = transforms.Compose([
         transforms.Resize((256,256)),
         transforms.ToTensor()
@@ -164,33 +164,33 @@ def preprocess_for_your_model(image):
     return val_test_transform(image).unsqueeze(0)  # Add batch dimension
 
 def predict_tumor(image, mask=None):
-    current_model = load_your_attention_model()
+    current_model = load_attention_model()
     
     if current_model is None:
-        return None, "Failed to load your trained model."
+        return None, "Failed to load trained model."
     if image is None:
         return None, "Please upload an image first."
     
     try:
-        print("Processing with YOUR trained Attention U-Net...")
+        print("Processing with PerceptNet Attention U-Net...")
         
-        # Use the exact preprocessing from your Colab code
-        input_tensor = preprocess_for_your_model(image).to(device)
+        # Preprocess image
+        input_tensor = preprocess_image(image).to(device)
         
-        # Predict using your model (exactly like your Colab code)
+        # Model prediction
         with torch.no_grad():
             pred_mask = torch.sigmoid(current_model(input_tensor))
             pred_mask_binary = (pred_mask > 0.5).float()
         
-        # Convert to numpy (like your Colab code)
+        # Convert to numpy
         pred_mask_np = pred_mask_binary.cpu().squeeze().numpy()
         prob_mask_np = pred_mask.cpu().squeeze().numpy()  # Probability for heatmap
         original_np = np.array(image.convert('L').resize((256, 256)))
         
-        # Create inverted mask for visualization (like your Colab code)
+        # Create inverted mask for visualization
         inv_pred_mask_np = np.where(pred_mask_np == 1, 0, 255)
         
-        # Create tumor-only image (like your Colab code)
+        # Create tumor-only image
         tumor_only = np.where(pred_mask_np == 1, original_np, 255)
         
         # Handle ground truth if provided
@@ -212,7 +212,7 @@ def predict_tumor(image, mask=None):
         
         # Create visualization (5-panel layout)
         fig, axes = plt.subplots(1, 5, figsize=(25, 5))
-        fig.suptitle('Your Attention U-Net Results', fontsize=16, fontweight='bold')
+        fig.suptitle('PerceptNet Analysis Results', fontsize=16, fontweight='bold')
         
         titles = ["Original Image", "Ground Truth", "Predicted Mask", "Tumor Only", "Heatmap"]
         images = [original_np, mask_np if mask_np is not None else np.zeros_like(original_np), inv_pred_mask_np, tumor_only, prob_mask_np]
@@ -233,7 +233,7 @@ def predict_tumor(image, mask=None):
         
         result_image = Image.open(buf)
         
-        # Calculate statistics (like your Colab code)
+        # Calculate statistics
         tumor_pixels = np.sum(pred_mask_np)
         total_pixels = pred_mask_np.size
         tumor_percentage = (tumor_pixels / total_pixels) * 100
@@ -243,7 +243,7 @@ def predict_tumor(image, mask=None):
         mean_confidence = torch.mean(pred_mask).item()
         
         analysis_text = f"""
-## Your Attention U-Net Analysis Results
+## PerceptNet Analysis Results
 ### Detection Summary:
 - **Status**: {'TUMOR DETECTED' if tumor_pixels > 50 else 'NO SIGNIFICANT TUMOR'}
 - **Tumor Area**: {tumor_percentage:.2f}% of brain region
@@ -256,35 +256,28 @@ def predict_tumor(image, mask=None):
 - **Dice Score**: {dice_score:.4f}
 - **IoU Score**: {iou_score:.4f}
 """
-        analysis_text += """
+        analysis_text += f"""
 ### Model Information:
-- **Architecture**: YOUR trained Attention U-Net
+- **Architecture**: PerceptNet Attention U-Net
 - **Training Performance**: Dice: 0.8420, IoU: 0.7297 
 - **Input**: Grayscale (single channel)
 - **Output**: Binary segmentation mask
 - **Device**: {device.type.upper()}
-### Model Performance:
-- **Training Accuracy**: 98.90%
-- **Best Dice Score**: 0.8420
-- **Best IoU Score**: 0.7297
-- **Training Dataset**: Brain tumor segmentation dataset
 ### Processing Details:
-- **Preprocessing**: Resize(256×256) + ToTensor (your exact method)
+- **Preprocessing**: Resize(256×256) + ToTensor
 - **Threshold**: 0.5 (sigmoid > 0.5)
 - **Architecture**: Attention gates + Skip connections
 - **Features**: [32, 64, 128, 256] channels
 ### Medical Disclaimer:
-This is YOUR trained AI model for **research and educational purposes only**. 
+This AI model is for **research and educational purposes only**. 
 Results should be validated by medical professionals. Not for clinical diagnosis.
-### Model Quality:
-This is your own trained model with {tumor_percentage:.2f}% detection capability!
         """
         
-        print(f"Your model analysis completed! Tumor area: {tumor_percentage:.2f}%")
+        print(f"Model analysis completed! Tumor area: {tumor_percentage:.2f}%")
         return result_image, analysis_text
         
     except Exception as e:
-        error_msg = f"Error with your model: {str(e)}"
+        error_msg = f"Error with model: {str(e)}"
         print(error_msg)
         return None, error_msg
 
@@ -293,113 +286,210 @@ def load_random_sample():
         return None, None, "Dataset not available."
     rand_idx = random.randint(0, len(test_imgs) - 1)
     img_path = os.path.join(image_path, test_imgs[rand_idx])
-    msk_path = os.path.join(mask_path, test_masks[rand_idx])  # Assuming paired by index
+    msk_path = os.path.join(mask_path, test_masks[rand_idx])
     image = Image.open(img_path).convert('L')
     mask = Image.open(msk_path).convert('L')
     return image, mask, "Loaded random sample from dataset."
 
 def clear_all():
-    return None, None, "Upload a brain MRI image to test YOUR trained Attention U-Net model", None
+    return None, None, "Upload a brain MRI image to test PerceptNet model", None
 
-# Enhanced CSS for your model
+# Professional CSS styling
 css = """
 .gradio-container {
-    max-width: 1400px !important;
+    max-width: 1600px !important;
     margin: auto !important;
+    background-color: #ffffff !important;
+    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif !important;
 }
-#title {
-    text-align: center;
-    background: linear-gradient(135deg, #8B5CF6 0%, #7C3AED 100%);
+
+#title-header {
+    background: linear-gradient(135deg, #2563eb 0%, #1d4ed8 100%);
     color: white;
+    padding: 40px 30px;
+    border-radius: 12px;
+    margin-bottom: 30px;
+    box-shadow: 0 4px 20px rgba(37, 99, 235, 0.15);
+    text-align: center;
+}
+
+.main-container {
+    background-color: #ffffff;
+    border-radius: 12px;
+    box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
     padding: 30px;
-    border-radius: 15px;
-    margin-bottom: 25px;
-    box-shadow: 0 8px 16px rgba(139, 92, 246, 0.3);
+    margin-bottom: 20px;
+}
+
+.input-section {
+    background-color: #f8fafc;
+    border: 1px solid #e2e8f0;
+    border-radius: 8px;
+    padding: 25px;
+}
+
+.info-panel {
+    background: linear-gradient(135deg, #f0f9ff 0%, #e0f2fe 100%);
+    border: 1px solid #0ea5e9;
+    border-radius: 8px;
+    padding: 20px;
+    margin-top: 20px;
+}
+
+.footer-section {
+    background-color: #f8fafc;
+    border: 1px solid #e2e8f0;
+    border-radius: 12px;
+    padding: 30px;
+    margin-top: 30px;
+}
+
+.stat-grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr;
+    gap: 30px;
+    margin: 20px 0;
+}
+
+.disclaimer-text {
+    color: #dc2626;
+    font-weight: 600;
+    line-height: 1.5;
+    background-color: #fef2f2;
+    padding: 15px;
+    border-radius: 6px;
+    border: 1px solid #fecaca;
+}
+
+h1, h2, h3, h4 {
+    color: #1e293b !important;
+}
+
+.gr-button-primary {
+    background: linear-gradient(135deg, #2563eb 0%, #1d4ed8 100%) !important;
+    border: none !important;
+    color: white !important;
+    font-weight: 600 !important;
+    padding: 12px 24px !important;
+    border-radius: 8px !important;
+    transition: all 0.2s ease !important;
+}
+
+.gr-button-primary:hover {
+    transform: translateY(-1px) !important;
+    box-shadow: 0 4px 12px rgba(37, 99, 235, 0.3) !important;
+}
+
+.gr-button-secondary {
+    background: #6b7280 !important;
+    border: none !important;
+    color: white !important;
+    font-weight: 600 !important;
+    padding: 12px 24px !important;
+    border-radius: 8px !important;
 }
 """
 
-# Create Gradio interface for your model
-with gr.Blocks(css=css, title="Your Attention U-Net Model", theme=gr.themes.Soft()) as app:
+# Create Gradio interface
+with gr.Blocks(css=css, title="PerceptNet - Brain Tumor Segmentation", theme=gr.themes.Default()) as app:
     
     gr.HTML("""
-    <div id="title">
-        <h1>Your Attention U-Net Model</h1>
-        <p style="font-size: 18px; margin-top: 15px;">
-            Using Your Own Trained Model • Dice: 0.8420 • IoU: 0.7297
+    <div id="title-header">
+        <h1 style="margin: 0; font-size: 2.5rem; font-weight: 700;">PerceptNet</h1>
+        <p style="font-size: 1.2rem; margin: 15px 0 5px 0; opacity: 0.95;">
+            Advanced Brain Tumor Segmentation System
         </p>
-        <p style="font-size: 14px; margin-top: 10px; opacity: 0.9;">
-            Loaded from: ArchCoder/the-op-segmenter HuggingFace Space
+        <p style="font-size: 1rem; margin: 5px 0 0 0; opacity: 0.8;">
+            Attention U-Net Architecture • Dice: 0.8420 • IoU: 0.7297
         </p>
     </div>
     """)
     
     mask_state = gr.State(None)
     
-    with gr.Row():
-        with gr.Column(scale=1):
-            gr.Markdown("### Upload Brain MRI")
+    with gr.Row(elem_classes="main-container"):
+        with gr.Column(scale=1, elem_classes="input-section"):
+            gr.Markdown("### Upload Brain MRI Scan", elem_classes="section-title")
             
             image_input = gr.Image(
-                label="Brain MRI Scan",
+                label="Brain MRI Image",
                 type="pil",
                 sources=["upload", "webcam"],
-                height=350
+                height=380
             )
             
             with gr.Row():
-                analyze_btn = gr.Button("Analyze with YOUR Model", variant="primary", scale=1, size="lg")
-                random_btn = gr.Button("Load Random Sample", variant="secondary", scale=1, size="lg")
-                clear_btn = gr.Button("Clear", variant="secondary", scale=1)
+                analyze_btn = gr.Button(
+                    "Analyze Image", 
+                    variant="primary", 
+                    scale=2,
+                    size="lg"
+                )
+                random_btn = gr.Button(
+                    "Load Sample", 
+                    variant="secondary", 
+                    scale=1,
+                    size="lg"
+                )
+                clear_btn = gr.Button(
+                    "Clear", 
+                    variant="secondary", 
+                    scale=1
+                )
             
             gr.HTML("""
-            <div style="margin-top: 20px; padding: 20px; background: linear-gradient(135deg, #F3E8FF 0%, #EDE9FE 100%); border-radius: 10px; border-left: 4px solid #8B5CF6;">
-                <h4 style="color: #8B5CF6; margin-bottom: 15px;">Your Model Features:</h4>
-                <ul style="margin: 10px 0; padding-left: 20px; line-height: 1.6;">
-                    <li><strong>Personal Model:</strong> Your own trained Attention U-Net</li>
-                    <li><strong>Proven Performance:</strong> 84.2% Dice Score, 72.97% IoU</li>
-                    <li><strong>Attention Gates:</strong> Advanced feature selection</li>
-                    <li><strong>Clean Output:</strong> Binary segmentation masks</li>
-                    <li><strong>5-Panel View:</strong> Complete analysis like your Colab</li>
-                </ul>
+            <div class="info-panel">
+                <h4 style="color: #0ea5e9; margin-bottom: 15px; font-size: 1.1rem;">Model Specifications</h4>
+                <div style="line-height: 1.8; font-size: 0.95rem;">
+                    <div><strong>Architecture:</strong> Attention U-Net with Skip Connections</div>
+                    <div><strong>Performance:</strong> 84.2% Dice Score, 72.97% IoU</div>
+                    <div><strong>Input Format:</strong> Grayscale MRI Scans (256×256)</div>
+                    <div><strong>Output:</strong> Binary Segmentation + Confidence Heatmap</div>
+                    <div><strong>Features:</strong> Attention Mechanisms, Multi-scale Analysis</div>
+                </div>
             </div>
             """)
         
         with gr.Column(scale=2):
-            gr.Markdown("### Your Model Results")
+            gr.Markdown("### Analysis Results", elem_classes="section-title")
             
             output_image = gr.Image(
-                label="Your Attention U-Net Analysis",
+                label="PerceptNet Analysis Output",
                 type="pil",
-                height=500
+                height=520
             )
             
             analysis_output = gr.Markdown(
-                value="Upload a brain MRI image to test YOUR trained Attention U-Net model.",
-                elem_id="analysis"
+                value="Upload a brain MRI image to begin analysis with PerceptNet.",
+                elem_id="analysis-results"
             )
-    # Footer highlighting your model
+    
+    # Footer section
     gr.HTML("""
-    <div style="margin-top: 30px; padding: 25px; background-color: #F8FAFC; border-radius: 15px; border: 2px solid #8B5CF6;">
-        <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 30px;">
+    <div class="footer-section">
+        <div class="stat-grid">
             <div>
-                <h4 style="color: #8B5CF6; margin-bottom: 15px;">Your Personal AI Model</h4>
-                <p><strong>Architecture:</strong> Attention U-Net with skip connections</p>
-                <p><strong>Performance:</strong> Dice: 0.8420, IoU: 0.7297, Accuracy: 98.90%</p>
-                <p><strong>Training:</strong> Your own dataset-specific training</p>
-                <p><strong>Features:</strong> [32, 64, 128, 256] channel progression</p>
+                <h4 style="color: #2563eb; margin-bottom: 15px;">Technical Specifications</h4>
+                <div style="line-height: 1.6;">
+                    <p><strong>Model Architecture:</strong> Attention U-Net with Gating Mechanisms</p>
+                    <p><strong>Training Dataset:</strong> Brain Tumor Segmentation Dataset</p>
+                    <p><strong>Image Processing:</strong> 256×256 Grayscale Normalization</p>
+                    <p><strong>Inference Speed:</strong> Real-time Processing on GPU/CPU</p>
+                    <p><strong>Output Formats:</strong> Binary Masks, Probability Maps, Heatmaps</p>
+                </div>
             </div>
             <div>
-                <h4 style="color: #DC2626; margin-bottom: 15px;">Your Model Disclaimer</h4>
-                <p style="color: #DC2626; font-weight: 600; line-height: 1.4;">
-                    This is YOUR personally trained AI model for <strong>research purposes only</strong>.<br>
-                    Results reflect your model's training performance.<br>
-                    Always validate with medical professionals for any clinical application.
-                </p>
+                <h4 style="color: #dc2626; margin-bottom: 15px;">Important Disclaimer</h4>
+                <div class="disclaimer-text">
+                    PerceptNet is an AI research tool designed for <strong>educational and research purposes only</strong>. 
+                    This system is not intended for clinical diagnosis or medical decision-making. 
+                    All results must be validated by qualified medical professionals before any medical application.
+                </div>
             </div>
         </div>
-        <hr style="margin: 20px 0; border: none; border-top: 2px solid #E5E7EB;">
-        <p style="text-align: center; color: #6B7280; margin: 10px 0; font-weight: 600;">
-            Your Personal Attention U-Net • Downloaded from HuggingFace • Research-Grade Performance
+        <hr style="margin: 25px 0; border: none; border-top: 1px solid #e2e8f0;">
+        <p style="text-align: center; color: #64748b; margin: 15px 0; font-weight: 500;">
+            PerceptNet v1.0 • Advanced Medical Image Analysis • Research Grade Performance
         </p>
     </div>
     """)
@@ -425,9 +515,9 @@ with gr.Blocks(css=css, title="Your Attention U-Net Model", theme=gr.themes.Soft
     )
 
 if __name__ == "__main__":
-    print("Starting YOUR Attention U-Net Model System...")
-    print("Using your personally trained model")
-    print("Auto-downloading from HuggingFace...")
+    print("Starting PerceptNet Brain Tumor Segmentation System...")
+    print("Loading Attention U-Net architecture...")
+    print("Auto-downloading model weights...")
     print("Expected performance: Dice 0.8420, IoU 0.7297")
     
     app.launch(