Update app.py

app.py

@@ -1,121 +1,107 @@
 # app.py
 
 import numpy as np
-np.int = int   # PaddleOCR’nin eski np.int kullanım yaması
+np.int = int   # patch for PaddleOCR’nin eski np.int çağrılarına
 
-import cv2, json, tempfile, re, gradio as gr
+import cv2, json, tempfile, re
+import gradio as gr
 from ultralytics import YOLO
 from paddleocr import PaddleOCR
 
 # ─── 1) Load models ───────────────────────────────────────────────
 yolo = YOLO("models/best.pt")
-
-ocr = PaddleOCR(
-    det=False,                    # OCR’nin kendi tespitini kapatıyoruz
-    rec=True,                     # sadece okuma
+ocr  = PaddleOCR(
+    det=False,                # Görüntü genel tespiti burada kapalı
+    rec=True,
     rec_model_dir="models/ocr_model",
-    rec_image_shape="3,32,128",   # inference.yml ile birebir aynı
-    cls=True,                     # açı sınıflandırıcısı
-    use_angle_cls=True,           # v2.x flag
-    use_space_char=True           # boşluk okumasına izin
+    use_textline_orientation=False,
+    lang="en"
 )
 
-# ─── 2) Plaka formatlayıcı ─────────────────────────────────────────
+# ─── 2) Turkish plate formatter ────────────────────────────────────
 def format_turkish_plate(s: str) -> str:
     s = re.sub(r'[^A-Z0-9]', '', s.upper())
     m = re.match(r'^(\d{2})([A-Z]{1,3})(\d{2,4})$', s)
     return f"{m.group(1)} {m.group(2)} {m.group(3)}" if m else "Unknown"
 
-# ─── 3) Görüntü pipeline ────────────────────────────────────────────
+# ─── yardımcı: OCR çıktısını normalize et ─────────────────────────
+def extract_text_score(recs):
+    if not recs:
+        return "", 0.0
+    first = recs[0]
+    # det=False ile dönen format: ["TEXT", score]
+    if isinstance(first, (list,tuple)) and len(first)==2 and isinstance(first[0], str):
+        return first[0], float(first[1])
+    # det=True formatı (eskiden): [["TEXT", score], …]
+    if isinstance(first, list) and first and isinstance(first[0], (list,tuple)):
+        return first[0][0], float(first[0][1])
+    # tanımadı
+    return "", 0.0
+
+# ─── 3) Single‐image inference ─────────────────────────────────────
 def run_image(img, conf=0.25):
     bgr = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
     res = yolo(bgr, conf=conf)[0]
     out = bgr.copy()
-
-    for box, _ in zip(res.boxes.xyxy.cpu().numpy(),
-                      res.boxes.conf.cpu().numpy()):
-        x1,y1,x2,y2 = box.astype(int)
+    for box in res.boxes.xyxy.cpu().numpy().astype(int):
+        x1,y1,x2,y2 = box
         crop = out[y1:y2, x1:x2]
-        if crop.size == 0: 
+        if crop.size == 0:
             continue
-
-        plate_img = cv2.resize(crop, (128, 32))
-
-        # dahili tespit kapalı, sadece tanıma+angle-cls
+        plate_img = cv2.resize(crop, (128,32))
         try:
-            recs = ocr.ocr(plate_img, det=False, cls=True)
+            recs = ocr.ocr(plate_img, det=False, cls=False)
         except Exception:
             recs = []
-
-        if recs:
-            raw_text, ocr_score = recs[0][0], recs[0][1]
-        else:
-            raw_text, ocr_score = "", 0.0
-
-        plate = format_turkish_plate(raw_text)
-        label = f"{plate} ({ocr_score:.2f})"
-
+        raw, score = extract_text_score(recs)
+        plate = format_turkish_plate(raw)
+        label = f"{plate} ({score:.2f})"
         cv2.rectangle(out, (x1,y1),(x2,y2), (0,255,0), 2)
         cv2.putText(out, label, (x1, y1-5),
                     cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
-
     return cv2.cvtColor(out, cv2.COLOR_BGR2RGB), f"{len(res.boxes)} plate(s) detected"
 
-# ─── 4) Video pipeline ─────────────────────────────────────────────
+# ─── 4) Video inference ───────────────────────────────────────────
 def run_video(video_file, conf=0.25):
     cap = cv2.VideoCapture(video_file)
     fps = cap.get(cv2.CAP_PROP_FPS)
     w  = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     h  = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    outfp = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
-    writer = cv2.VideoWriter(outfp, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w,h))
-    records, idx = [], 0
-
+    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
+    writer = cv2.VideoWriter(tmp_out, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w,h))
+    records = []
+    idx = 0
     while True:
         ret, frame = cap.read()
         if not ret: break
-        idx += 1; t = idx / fps
-
+        idx += 1; t = idx/fps
         res = yolo(frame, conf=conf)[0]
-        for (x1,y1,x2,y2) in res.boxes.xyxy.cpu().numpy().astype(int):
+        for box in res.boxes.xyxy.cpu().numpy().astype(int):
+            x1,y1,x2,y2 = box
             crop = frame[y1:y2, x1:x2]
-            if crop.size == 0: 
+            if crop.size == 0:
                 continue
-
-            plate_img = cv2.resize(crop, (128, 32))
+            plate_img = cv2.resize(crop, (128,32))
             try:
-                recs = ocr.ocr(plate_img, det=False, cls=True)
+                recs = ocr.ocr(plate_img, det=False, cls=False)
             except Exception:
                 recs = []
-
-            if recs:
-                raw_text, ocr_score = recs[0][0], recs[0][1]
-            else:
-                raw_text, ocr_score = "", 0.0
-
-            plate = format_turkish_plate(raw_text)
+            raw, score = extract_text_score(recs)
+            plate = format_turkish_plate(raw)
             if plate != "Unknown":
-                records.append({
-                    "time_s": round(t,2),
-                    "plate": plate,
-                    "conf":  round(ocr_score,3)
-                })
-
+                records.append({"time_s":round(t,2),"plate":plate,"conf":round(score,3)})
             cv2.rectangle(frame, (x1,y1),(x2,y2), (0,255,0), 2)
             cv2.putText(frame, plate, (x1, y1-5),
                         cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
-
         writer.write(frame)
-
     cap.release(); writer.release()
     with open("output.json","w") as f:
         json.dump(records, f, indent=2)
-    return outfp, "Done"
+    return tmp_out, "Done"
 
 # ─── 5) Gradio UI ──────────────────────────────────────────────────
 with gr.Blocks() as demo:
     gr.Markdown("## 🚗 License Plate Detection + Recognition")
-
     with gr.Row():
         with gr.Column():
             img_in = gr.Image(type="numpy", label="Upload Image")
@@ -127,9 +113,8 @@ with gr.Blocks() as demo:
             img_out = gr.Image(type="numpy", label="Annotated Image")
             vid_out = gr.Video(label="Annotated Video")
             status  = gr.Textbox(label="Status / JSON Path")
-
     b1.click(run_image, [img_in,conf], [img_out,status])
     b2.click(run_video, [vid_in,conf], [vid_out,status])
 
-if __name__ == "__main__":
+if __name__=="__main__":
     demo.launch()