Upload 3 files

app.py

@@ -1,64 +1,89 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+import cv2
+from ultralytics import YOLO
+import tempfile
+import os
+
+# Charger le modèle
+model = YOLO("yolo12m.pt")  # ou yolov8n.pt
+
+# Classes à détecter
+target_classes = ["backpack", "suitcase", "handbag"]
+class_name_to_id = {name: idx for idx, name in model.names.items()}
+target_ids = [class_name_to_id[c] for c in target_classes]
+
+def process_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+    ret, frame = cap.read()
+    if not ret:
+        return "Erreur lecture vidéo"
+
+    H, W = frame.shape[:2]
+    line_y = int(H * 0.6)
+    tolerance = 25
+
+    counted_ids = set()
+    class_counts = {c: 0 for c in target_classes}
+    total_count = 0
+
+    # Output temporaire
+    temp_out = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(temp_out.name, fourcc, 20, (W, H))
+
+    cap.set(cv2.CAP_PROP_POS_FRAMES, 0)
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        results = model.track(frame, persist=True, classes=target_ids, verbose=False)
+
+        if results[0].boxes.id is not None:
+            ids = results[0].boxes.id.int().cpu().tolist()
+            clss = results[0].boxes.cls.int().cpu().tolist()
+            boxes = results[0].boxes.xyxy.cpu().tolist()
+
+            for obj_id, cls, box in zip(ids, clss, boxes):
+                x1, y1, x2, y2 = map(int, box)
+                center_x = (x1 + x2) // 2
+                center_y = (y1 + y2) // 2
+                class_name = model.names[cls]
+
+                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                cv2.putText(frame, f"{class_name} ID:{obj_id}", (x1, y1 - 10),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+
+                if obj_id not in counted_ids and (line_y - tolerance < center_y < line_y + tolerance):
+                    counted_ids.add(obj_id)
+                    total_count += 1
+                    class_counts[class_name] += 1
+
+        # Affichage des résultats
+        y_offset = 30
+        for name in target_classes:
+            cv2.putText(frame, f"{name}: {class_counts[name]}", (20, y_offset),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 255), 2)
+            y_offset += 30
+        cv2.putText(frame, f"Total: {total_count}", (20, y_offset + 10),
+                    cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
+        cv2.line(frame, (0, line_y), (W, line_y), (0, 0, 255), 2)
+
+        out.write(frame)
+
+    cap.release()
+    out.release()
+    return temp_out.name
+
+# Interface Gradio
+demo = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Importer une vidéo de bagages"),
+    outputs=gr.Video(label="Vidéo annotée avec comptage"),
+    title="🎒 Compteur intelligent de bagages",
+    description="Détecte et compte les sacs, valises, et sacs à dos avec YOLO."
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+opencv-python==4.11.0.86
+deep-sort-realtime==1.3.1
+ultralytics==8.3.141
+gradio

yolo12m.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6d179786eddf6134ee469ae2f4ce04cbe4e9d1a47d6b669d9cd6b9c6c513d8
+size 40904955