Update main.py

main.py

@@ -12,6 +12,7 @@ from fastapi.responses import StreamingResponse
 from utils import tts, read_image_file, pil_to_base64, get_hist
 from typing import Optional
 from huggingface_hub import hf_hub_download
+import time
 
 from io import BytesIO
 import zipfile
@@ -42,6 +43,8 @@ async def predict_api(
     most_close = 0
     out_img = None
     diff_value = 0.5
+    total_time = time.time()
+    start_time = time.time()
     if boxes is not None:
         for xyxy, conf, cls in zip(boxes.xyxy, boxes.conf, boxes.cls):
             if int(cls) != 0:
@@ -51,20 +54,26 @@ async def predict_api(
             if area_rate >= most_close:
                 out_img = image.crop(tuple(box)).resize((64, 64))
                 most_close = area_rate
+    print("Yolo time", time.time() - start_time)
+    start_time = time.time()
     if last_seen is not None:
         last_seen = read_image_file(await last_seen.read())
         if out_img is not None:
             diff_value = dist.euclidean(get_hist(out_img), get_hist(last_seen))
-    print(most_close, diff_value)
+    print("Hist time", time.time() - start_time)
+    start_time = time.time()
+    print(f"Distance: {most_close}. Different value: {diff_value}")
     if most_close >= area_thres and diff_value >= 0.5:
         voice_bot_path = tts(defaul_bot_voice, language="ja")
         image_bot_path = pil_to_base64(out_img)
+        print("Voice time", time.time() - start_time)
         io = BytesIO()
         zip_filename = "final_archive.zip"
         with zipfile.ZipFile(io, mode='w', compression=zipfile.ZIP_DEFLATED) as zf:
             for file_path in [voice_bot_path, image_bot_path]:
                 zf.write(file_path)
             zf.close()
+        print("Total time", time.time() - total_time)
         return StreamingResponse(
             iter([io.getvalue()]),
             media_type="application/x-zip-compressed",