Merge pull request #19 from 5sControl/dev

Dev

.gitignore

@@ -24,6 +24,7 @@
 .vscode/
 *.env           
 test.py
+*.pt
 
 storage.googleapis.com
 runs/*

confs/settings.env

@@ -9,7 +9,6 @@ extra = '
             {
                 "itemId": 39,
                 "itemName": "tea",
-                "multiRow": false,
                 "task": "bottles",
                 "lowStockLevel": 20,
                 "coords": [
@@ -20,6 +19,20 @@ extra = '
                         "y2": 464.53088357256775
                     }
                 ]
+            },
+            {
+                "itemId": 28,
+                "itemName": "tea",
+                "task": "red lines",
+                "lowStockLevel": 10,
+                "coords": [
+                    {
+                        "x1": 495.8731636363636,
+                        "x2": 1417.4731636363636,
+                        "y1": 186.89133014354067,
+                        "y2": 464.53088357256775
+                    }
+                ]
             }
         ],
         "zones": []

min_max_utils/MinMaxReporter.py

@@ -50,7 +50,7 @@ def create_report(self, n_boxes_history: list, img: np.array, areas: list, boxes
             report.append(zone_dict)
         for item_index, item in enumerate(areas):
             itemid = item['itemId']
-            multi_row = item['multiRow']
+            multi_row = item['task'] == 'red lines'
 
             item_name = item['itemName']
             user_dbg_image_name_url = self.user_folder + '/' + str(uuid.uuid4()) + '.png'

model_image/app.py

@@ -10,6 +10,7 @@
 app = Flask(__name__)
 human_model = ObjDetectionModel(HUMAN_MODEL_PATH, CONF_THRES, IOU_THRES, CLASSES)
 box_model = ObjDetectionModel(BOX_MODEL_PATH, CONF_THRES, IOU_THRES, CLASSES)
+bottle_model = ObjDetectionModel(BOTTLE_MODEL_PATH, CONF_THRES, IOU_THRES, CLASSES)
 
 
 logger = logging.getLogger('min_max_logger')
@@ -56,7 +57,7 @@ def predict_boxes():
 def predict_bottles():
     if request.method == 'POST':
         image = np.array(request.json['image']).astype(np.float32)
-        n_bottles, coords = human_model(image, classes=[39])
+        n_bottles, coords = bottle_model(image)
         logger.info("Request to predict_bottles: " + str(n_bottles))
         return jsonify(
             {

model_image/flask_configs/flask_confs.json

@@ -6,6 +6,7 @@
     "conf_thres": 0.46,
     "box_detect_model": "min_max_v0.3.10.pt",
     "human_detect_model": "min_max_v1.0h.pt",
+    "bottle_detect_model": "min_max_v0.4.3b.pt",
     "img_size": 640,
     "port": 5000
 }

model_image/flask_configs/load_configs.py

@@ -7,6 +7,7 @@
     IOU_THRES = configs.get("iou_thres")
     BOX_MODEL_PATH = configs.get("box_detect_model")
     HUMAN_MODEL_PATH = configs.get("human_detect_model")
+    BOTTLE_MODEL_PATH = configs.get("bottle_detect_model")
     CLASSES = configs.get("classes")
     IMG_SIZE = configs.get("img_size")
     PORT = configs.get("port")

model_image/requirements.txt

@@ -8,5 +8,5 @@ pydantic==1.10.2
 python-dotenv==1.0.0
 PyYAML==6.0
 requests==2.27.1
-ultralytics==8.0.112
+ultralytics==8.0.136
 Flask==2.2.2