fix artifacts vs cache

backend/video_capture.py

 import cv2
 from datetime import datetime, timedelta
-import numpy as np
-import keras
 from utils.preprocessing import fix_singular_shape, norm_by_imagenet
+from dotenv import load_dotenv
+import numpy as np
+import requests
 import json
 import time
+import os
 
 from cameras import restaurants
 from db import models
 from db.database import SessionLocal
 from routers.websocket import manager
 
+load_dotenv()
+host = os.getenv('MODEL_HOST')
+port = os.getenv('MODEL_PORT')
+model = os.getenv('MODEL_NAME')
+
+
+def make_prediction(instances):
+    url = f"http://{host}:{port}/v1/models/{model}:predict"
+    data = json.dumps({"signature_name": "serving_default", "instances": instances.tolist()})
+    headers = {"content-type": "application/json"}
+    json_response = requests.post(url, data=data, headers=headers)
+    try:
+        predictions = json.loads(json_response.text)['predictions']
+    except BaseException:
+        print("prediction failed")
+    return predictions
+
 
 async def handle_cameras():
-    model = keras.models.load_model('assets', compile=False)
+
     db = SessionLocal()
     for restaurant in restaurants:
         for camera in restaurant["cameras"]:
@@ -58,7 +77,7 @@ async def handle_cameras():
                                         [treated_img]))),
                             axis=0)
                         # getting the density map from the model and the number of people
-                        pred_map = np.squeeze(model.predict(input_image, verbose=0))
+                        pred_map = np.squeeze(make_prediction(input_image))
                         count_prediction += np.sum(pred_map)
                         for checkout in camera["checkouts"]:
                             # we check whether or not the density in the checkout area is high enough to determine if it is open or not