Create app.py

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import mlflow
+import dagshub
+from ultralytics import YOLO
+from PIL import Image
+import cv2
+import numpy as np
+import os
+import time
+import tempfile
+import shutil
+
+# ==============================
+# MLflow / DagsHub Configuration using Secrets
+# ==============================
+# Secrets من HF Spaces
+tracking_uri = os.getenv("MLFLOW_TRACKING_URI")
+username = os.getenv("MLFLOW_TRACKING_USERNAME")
+password = os.getenv("MLFLOW_TRACKING_PASSWORD")
+
+if not all([tracking_uri, username, password]):
+    raise ValueError("MLflow Secrets مش مظبوطة! روح لـ Space Settings → Secrets وتأكد من الأسماء")
+
+os.environ["MLFLOW_TRACKING_URI"] = tracking_uri
+os.environ["MLFLOW_TRACKING_USERNAME"] = username
+os.environ["MLFLOW_TRACKING_PASSWORD"] = password
+
+# تفعيل DagsHub
+dagshub.init(repo_owner="Mosensei7", repo_name="AutonomousVehiclesDetectionDEPI", mlflow=True)
+
+# إنشاء experiment
+mlflow.set_experiment("YOLOv12s_Inference_Logs")
+
+print("MLflow connected successfully to DagsHub!")
+
+# ==============================
+# Load Model
+# ==============================
+model = YOLO("Mosensei7/yolov12s-egyptian-autonomous-vehicles/best.pt")  # اسم الـ repo بتاعك
+
+# ==============================
+# Inference with Full MLflow Tracking
+# ==============================
+def run_inference(media_file, media_type):
+    if media_file is None:
+        return None, None, "ارفع ملف أولاً"
+
+    media_path = media_file.name
+
+    with mlflow.start_run(run_name=f"Inference_{int(time.time())}") as run:
+        mlflow.log_param("media_type", media_type)
+        mlflow.log_param("model", "YOLOv12s")
+        mlflow.log_param("timestamp", time.strftime("%Y-%m-%d %H:%M:%S"))
+
+        if media_type == "Image":
+            img = Image.open(media_path).convert("RGB")
+            img_array = np.array(img)
+
+            results = model(img_array)[0]
+            annotated = results.plot()
+            output_img = Image.fromarray(annotated[..., ::-1])  # BGR → RGB
+
+            # حفظ مؤقت ورفع artifacts
+            with tempfile.TemporaryDirectory() as tmpdir:
+                in_path = os.path.join(tmpdir, "input.jpg")
+                out_path = os.path.join(tmpdir, "output.jpg")
+                img.save(in_path)
+                output_img.save(out_path)
+
+                mlflow.log_artifact(in_path, artifact_path="input")
+                mlflow.log_artifact(out_path, artifact_path="output")
+
+            detections = len(results.boxes) if results.boxes is not None else 0
+            mlflow.log_metric("detections_count", detections)
+
+            run_url = f"https://dagshub.com/Mosensei7/AutonomousVehiclesDetectionDEPI/mlflow/#/experiments/{mlflow.get_experiment_by_name('YOLOv12s_Inference_Logs').experiment_id}/runs/{run.info.run_id}"
+
+            return output_img, None, f"✅ تم التسجيل!\nRun ID: {run.info.run_id}\n[شوف الـ Log على DagsHub]({run_url})"
+
+        else:  # Video
+            cap = cv2.VideoCapture(media_path)
+            fps = cap.get(cv2.CAP_PROP_FPS) or 30
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+            output_video = "output_video.mp4"
+            writer = cv2.VideoWriter(output_video, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+
+            frame_count = 0
+            total_detections = 0
+
+            while cap.isOpened():
+                ret, frame = cap.read()
+                if not ret:
+                    break
+                results = model(frame)[0]
+                annotated = results.plot()
+                writer.write(annotated)
+                frame_count += 1
+                total_detections += len(results.boxes) if results.boxes is not None else 0
+
+            cap.release()
+            writer.release()
+
+            # رفع الفيديوهات
+            mlflow.log_artifact(media_path, artifact_path="input_video")
+            mlflow.log_artifact(output_video, artifact_path="output_video")
+
+            mlflow.log_metric("frames_processed", frame_count)
+            mlflow.log_metric("total_detections", total_detections)
+            mlflow.log_metric("avg_detections_per_frame", total_detections / frame_count if frame_count > 0 else 0)
+
+            run_url = f"https://dagshub.com/Mosensei7/AutonomousVehiclesDetectionDEPI/mlflow/#/experiments/{mlflow.get_experiment_by_name('YOLOv12s_Inference_Logs').experiment_id}/runs/{run.info.run_id}"
+
+            # حذف الفيديو المؤقت عشان المساحة
+            if os.path.exists(output_video):
+                os.remove(output_video)
+
+            return None, output_video, f"✅ تم التسجيل!\nRun ID: {run.info.run_id}\n[شوف الـ Log على DagsHub]({run_url})"
+
+# ==============================
+# Futuristic UI (الأجمل على الإطلاق)
+# ==============================
+css = """
+body { background: linear-gradient(135deg, #0f0c29, #302b63, #24243e); color: #00ffff; font-family: 'Orbitron', sans-serif; }
+.gradio-container { max-width: 1100px; margin: auto; background: rgba(0,0,0,0.8); border: 3px solid #00ffff; border-radius: 30px; padding: 40px; box-shadow: 0 0 50px #00ffff; }
+h1 { text-align: center; color: #00ffff; text-shadow: 0 0 20px #00ffff; font-size: 3.2em; }
+button { background: linear-gradient(45deg, #ff00ff, #00ffff); border: none; border-radius: 20px; height: 60px; font-size: 1.3em; box-shadow: 0 0 25px #00ffff; }
+"""
+
+with gr.Blocks(css=css, theme=gr.themes.Dark()) as demo:
+    gr.Markdown("""
+    # 🚀 YOLOv12s - كشف المركبات في الشوارع المصرية 🇪🇬
+    **كل عملية كشف بتترفع تلقائيًا على DagsHub MLflow مع الـ input والـ output والإحصائيات**
+    """)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            media = gr.File(label="📤 ارفع صورة أو فيديو", file_types=[".jpg", ".jpeg", ".png", ".mp4", ".avi"])
+            media_type = gr.Radio(["Image", "Video"], label="نوع الميديا", value="Image")
+            btn = gr.Button("🚀 ابدأ الكشف", variant="primary", size="lg")
+
+        with gr.Column(scale=2):
+            img_out = gr.Image(label="🖼️ نتيجة الكشف", height=600)
+            vid_out = gr.Video(label="🎥 نتيجة الكشف", height=600)
+            info = gr.Markdown("**جاهز للكشف...**")
+
+    btn.click(
+        fn=run_inference,
+        inputs=[media, media_type],
+        outputs=[img_out, vid_out, info]
+    )
+
+demo.launch()