Allow multiple-model serving from Flask REST API (#8973)

utils/flask_rest_api/restapi.py

 # YOLOv5 🚀 by Ultralytics, GPL-3.0 license
 """
-Run a Flask REST API exposing a YOLOv5s model
+Run a Flask REST API exposing one or more YOLOv5s models
 """
 
 import argparse
@@ -11,12 +11,13 @@ from flask import Flask, request
 from PIL import Image
 
 app = Flask(__name__)
+models = {}
 
-DETECTION_URL = "/v1/object-detection/yolov5s"
+DETECTION_URL = "/v1/object-detection/<model>"
 
 
 @app.route(DETECTION_URL, methods=["POST"])
-def predict():
+def predict(model):
     if request.method != "POST":
         return
 
@@ -30,17 +31,18 @@ def predict():
         im_bytes = im_file.read()
         im = Image.open(io.BytesIO(im_bytes))
 
-        results = model(im, size=640)  # reduce size=320 for faster inference
-        return results.pandas().xyxy[0].to_json(orient="records")
+        if model in models:
+            results = models[model](im, size=640)  # reduce size=320 for faster inference
+            return results.pandas().xyxy[0].to_json(orient="records")
 
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
     parser.add_argument("--port", default=5000, type=int, help="port number")
+    parser.add_argument('--model', nargs='+', default=['yolov5s'], help='model(s) to run, i.e. --model yolov5n yolov5s')
     opt = parser.parse_args()
 
-    # Fix known issue urllib.error.HTTPError 403: rate limit exceeded https://github.com/ultralytics/yolov5/pull/7210
-    torch.hub._validate_not_a_forked_repo = lambda a, b, c: True
+    for m in opt.model:
+        models[m] = torch.hub.load("ultralytics/yolov5", m, force_reload=True, skip_validation=True)
 
-    model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True)  # force_reload to recache
     app.run(host="0.0.0.0", port=opt.port)  # debug=True causes Restarting with stat