Update app.py

app.py

@@ -11,35 +11,30 @@ import warnings
 warnings.filterwarnings('ignore')
 
 # ============================================================
-# 1. LOAD MODELS (مرة واحدة فقط)
+# 1. LOAD MODELS (CHANGE USERNAME BELOW)
 # ============================================================
 print("Loading YOLOv11 model from Hugging Face Hub...")
+# ⚠️ IMPORTANT: Replace "YOUR_USERNAME" with your actual Hugging Face username
 model_path = hf_hub_download(
-    repo_id="SkyGuardAI/drone-detection-yolov11",  # <--- غيّر هذا
+    repo_id="SkyGuardAI/drone-detection-yolov11",  # <--- CHANGE THIS
     filename="best.pt"
 )
 model = YOLO(model_path)
 print("YOLO model loaded successfully.")
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-# تفعيل half precision إذا كان الجهاز يدعمه (GPU أو CPU حديث)
-use_fp16 = device == "cuda" or (hasattr(torch, 'has_mps') and torch.has_mps)
-print(f"Using device: {device}, FP16: {use_fp16}")
+print(f"Using device: {device}")
 
 print("Loading BLIP model...")
 blip_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
-if use_fp16:
-    blip_model = blip_model.half()  # تقليل الدقة للنصف
 blip_model.eval()
 print("BLIP model loaded successfully.")
 
 # ============================================================
-# 2. HEATMAP FUNCTIONS (محسّنة)
+# 2. HEATMAP FUNCTIONS (unchanged)
 # ============================================================
 layer_outputs = {}
-# تعريف الألوان مرة واحدة خارج الدالة
-COLORMAP_JET = cv2.COLORMAP_JET
 
 def hook_fn(module, input, output):
     layer_outputs['feature_map'] = output.detach()
@@ -59,8 +54,9 @@ def get_best_layer(model):
 def generate_heatmap(model, image):
     try:
         layer_outputs.clear()
-        # تقليل حجم الصورة للخريطة الحرارية (تسريع كبير)
-        img_resized = cv2.resize(image, (320, 320))  # كان 640×640
+        if isinstance(image, Image.Image):
+            image = np.array(image)
+        img_resized = cv2.resize(image, (640, 640))
         pytorch_model = model.model if hasattr(model, 'model') else model
         target_layer = get_best_layer(pytorch_model)
         if target_layer is None:
@@ -82,39 +78,34 @@ def generate_heatmap(model, image):
             heatmap = (heatmap - min_val) / (max_val - min_val)
         else:
             heatmap = np.zeros_like(heatmap)
-        # إعادة التكبير إلى 640×640 بعد المعالجة (للحفاظ على جودة العرض)
         heatmap = cv2.resize(heatmap, (640, 640))
         threshold = np.percentile(heatmap, 70)
         heatmap = np.where(heatmap > threshold, heatmap, 0)
         if heatmap.max() > 0:
             heatmap = heatmap / heatmap.max()
-        heatmap_colored = cv2.applyColorMap((heatmap * 255).astype(np.uint8), COLORMAP_JET)
+        heatmap_colored = cv2.applyColorMap((heatmap * 255).astype(np.uint8), cv2.COLORMAP_JET)
         heatmap_colored = cv2.cvtColor(heatmap_colored, cv2.COLOR_BGR2RGB)
-        # تكبير الخريطة النهائية لتتناسب مع الصورة الأصلية (تتم خارج الدالة)
-        return heatmap_colored
+        overlay = cv2.addWeighted(img_resized, 0.6, heatmap_colored, 0.4, 0)
+        return overlay
     except Exception as e:
         print(f"Heatmap error: {e}")
         return None
 
 # ============================================================
-# 3. DYNAMIC CAPTION (BLIP) - مع FP16 و تقليل حجم الصورة
+# 3. DYNAMIC CAPTION (BLIP)
 # ============================================================
 def generate_dynamic_caption(image):
     try:
-        # تقليل حجم الصورة قبل تمريرها إلى BLIP (تسريع كبير)
-        if image.shape[0] > 480 or image.shape[1] > 480:
-            image_small = cv2.resize(image, (480, 480))
-        else:
-            image_small = image
-        pil_image = Image.fromarray(image_small).convert('RGB')
-        inputs = blip_processor(pil_image, return_tensors="pt").to(device)
-        if use_fp16:
-            inputs = {k: v.half() for k, v in inputs.items()}
+        if isinstance(image, np.ndarray):
+            image = Image.fromarray(image).convert('RGB')
+        elif isinstance(image, Image.Image):
+            image = image.convert('RGB')
+        inputs = blip_processor(image, return_tensors="pt").to(device)
         with torch.no_grad():
             out = blip_model.generate(
                 **inputs,
-                max_length=40,          # قللنا من 60 إلى 40
-                num_beams=3,            # قللنا من 5 إلى 3
+                max_length=60,
+                num_beams=5,
                 temperature=0.7,
                 repetition_penalty=1.2
             )
@@ -125,10 +116,9 @@ def generate_dynamic_caption(image):
         return "AI model is analyzing the scene."
 
 # ============================================================
-# 4. XAI REPORT (بدون تغيير)
+# 4. XAI REPORT
 # ============================================================
 def build_xai_report(is_drone, confidence, drone_count, processing_time, image_caption):
-    # ... (نفس الكود السابق، لم يتغير) ...
     if is_drone:
         drone_text = "a drone" if drone_count == 1 else f"{drone_count} drones"
         if confidence >= 0.8:
@@ -220,7 +210,7 @@ Scattered activation pattern confirms absence of strong drone-like features.
     return report
 
 # ============================================================
-# 5. MAIN PIPELINE FUNCTION (محسّنة)
+# 5. MAIN PIPELINE FUNCTION
 # ============================================================
 def drone_detection_pipeline(input_image):
     try:
@@ -229,24 +219,10 @@ def drone_detection_pipeline(input_image):
         else:
             img = input_image.copy()
         
-        # تقليل حجم الصورة قبل المعالجة (تسريع كبير)
         original_h, original_w = img.shape[:2]
-        # تغيير الحجم إلى 640×640 إذا كانت الصورة أكبر
-        if original_h > 640 or original_w > 640:
-            scale = 640 / max(original_h, original_w)
-            new_w = int(original_w * scale)
-            new_h = int(original_h * scale)
-            img_small = cv2.resize(img, (new_w, new_h))
-        else:
-            img_small = img
-        
-        # 1. الكشف باستخدام YOLO على الصورة المصغرة
-        results = model(img_small)
-        
-        # 2. الخريطة الحرارية (تعمل على الصورة المصغرة أيضاً)
-        heatmap_overlay = generate_heatmap(model, img_small)
+        results = model(img)
+        heatmap_overlay = generate_heatmap(model, img)
         
-        # 3. استخراج معلومات الكشف
         is_drone = False
         confidence = 0.0
         drone_count = 0
@@ -264,21 +240,16 @@ def drone_detection_pipeline(input_image):
                             confidence = max(confidence, conf)
         is_drone = drone_count > 0
         
-        # 4. إعادة رسم الصورة مع المربعات (نستخدم الصورة الأصلية للحفاظ على الجودة)
-        result_img = results[0].plot() if len(results) > 0 else img_small
+        result_img = results[0].plot() if len(results) > 0 else img
         result_img_rgb = cv2.cvtColor(result_img, cv2.COLOR_BGR2RGB)
+        caption = generate_dynamic_caption(img)
+        processing_time_ms = 0
+        report = build_xai_report(is_drone, confidence, drone_count, processing_time_ms, caption)
         
-        # 5. إنشاء الوصف النصي (يتم على الصورة المصغرة لتسريع BLIP)
-        caption = generate_dynamic_caption(img_small)
-        
-        # 6. بناء التقرير
-        report = build_xai_report(is_drone, confidence, drone_count, 0, caption)
-        
-        # 7. معالجة الخريطة الحرارية لتتناسب مع أبعاد الصورة الأصلية
         if heatmap_overlay is not None:
             heatmap_resized = cv2.resize(heatmap_overlay, (original_w, original_h))
         else:
-            heatmap_resized = np.zeros((original_h, original_w, 3), dtype=np.uint8)
+            heatmap_resized = np.zeros_like(result_img_rgb)
         
         return result_img_rgb, heatmap_resized, report
     except Exception as e:
@@ -288,14 +259,28 @@ def drone_detection_pipeline(input_image):
         return blank, blank, error_msg
 
 # ============================================================
-# 6. INTERFACE - مع إضافة queue() لتحسين الاستجابة
+# 6. INTERFACE - DARK BLUE ONLY, NO PURPLE/VIOLET
 # ============================================================
 custom_css = """
-/* (نفس CSS السابق، لم يتغير) */
-.gradio-container, body, .gradio-container .main {
+/* Force white background */
+.gradio-container, body, .gradio-container .main, .gradio-container .gradio-container {
     background: #ffffff !important;
     font-family: 'Segoe UI', 'Roboto', sans-serif;
 }
+/* Override any purple/violet colors from Gradio default theme */
+:root {
+    --primary-50: #0a2b4e !important;
+    --primary-100: #1e4a76 !important;
+    --primary-200: #2c5282 !important;
+    --primary-300: #1e3a8a !important;
+    --primary-400: #0a2b4e !important;
+    --primary-500: #0a2b4e !important;
+    --primary-600: #0a2b4e !important;
+    --primary-700: #0a2b4e !important;
+    --primary-800: #0a2b4e !important;
+    --primary-900: #0a2b4e !important;
+}
+/* Header - dark blue */
 .skyguard-header {
     text-align: center;
     padding: 1.5rem 0 0.5rem 0;
@@ -320,20 +305,25 @@ custom_css = """
     color: #2c5282 !important;
     margin-top: 0.5rem;
 }
-.gr-button-primary {
+/* Primary button - solid dark blue, no gradient, no purple */
+.gr-button-primary, button.gr-button-primary, .gr-button.primary {
     background: #0a2b4e !important;
     border: none !important;
     color: white !important;
     font-weight: 700 !important;
     border-radius: 30px !important;
     padding: 10px 28px !important;
+    transition: all 0.2s ease !important;
     text-transform: uppercase !important;
     letter-spacing: 1px;
+    box-shadow: none !important;
 }
-.gr-button-primary:hover {
+.gr-button-primary:hover, button.gr-button-primary:hover, .gr-button.primary:hover {
     background: #1e4a76 !important;
     transform: scale(1.02);
+    box-shadow: 0 2px 8px rgba(10,43,78,0.2) !important;
 }
+/* Tabs - remove purple */
 .gr-tabs .tab-nav button {
     background-color: #eef2f5 !important;
     color: #0a2b4e !important;
@@ -341,11 +331,28 @@ custom_css = """
     border-radius: 8px 8px 0 0 !important;
     padding: 8px 20px !important;
     margin-right: 4px;
+    border: none !important;
 }
 .gr-tabs .tab-nav button.selected {
     background-color: #0a2b4e !important;
     color: white !important;
 }
+/* Input and output boxes */
+.gr-box, .gr-form, .gr-input, .gr-panel {
+    background-color: #f9fafb !important;
+    border: 1px solid #d1d5db !important;
+    border-radius: 12px !important;
+}
+/* Labels */
+label, .gr-form label {
+    color: #1e293b !important;
+    font-weight: 500 !important;
+}
+/* Markdown text */
+.gr-markdown p, .gr-markdown {
+    color: #1e293b !important;
+}
+/* Footer */
 .skyguard-footer {
     text-align: center;
     margin-top: 30px;
@@ -354,6 +361,17 @@ custom_css = """
     border-top: 1px solid #e2e8f0;
     padding-top: 15px;
 }
+/* Additional overrides for any purple elements */
+.gr-button, .gr-button-lg, .gr-button-sm, button {
+    --tw-ring-color: #0a2b4e !important;
+}
+.prose a, a {
+    color: #1e4a76 !important;
+}
+input:focus, textarea:focus, select:focus {
+    border-color: #0a2b4e !important;
+    ring-color: #0a2b4e !important;
+}
 """
 
 with gr.Blocks(title="SkyGuard - Drone Detection System", theme=gr.themes.Soft(), css=custom_css) as demo:
@@ -392,8 +410,7 @@ with gr.Blocks(title="SkyGuard - Drone Detection System", theme=gr.themes.Soft()
     """)
 
 # ============================================================
-# 7. RUN APP - مع إضافة queue() لتحسين تدفق الطلبات
+# 7. RUN APP
 # ============================================================
 if __name__ == "__main__":
-    demo.queue(default_concurrency_limit=1)  # معالجة طلب واحد فقط في كل مرة
     demo.launch()