update

ieemoo-ai-isempty.py

@@ -13,6 +13,23 @@ from torchvision import transforms
 from models.modeling import VisionTransformer, CONFIGS
 sys.path.insert(0, ".")
 
+import logging.config
+from skywalking import agent, config
+SW_SERVER = os.environ.get('SW_AGENT_COLLECTOR_BACKEND_SERVICES')
+SW_SERVICE_NAME = os.environ.get('SW_AGENT_NAME')
+if SW_SERVER and SW_SERVICE_NAME:
+    config.init() #采集服务的地址，给自己的服务起个名称
+    #config.init(collector="123.60.56.51:11800", service='ieemoo-ai-search') #采集服务的地址，给自己的服务起个名称
+    agent.start()
+def setup_logging(path):
+    if os.path.exists(path):
+        with open(path, 'r') as f:
+            config = json.load(f)
+            logging.config.dictConfig(config)
+            logger = logging.getLogger("root")
+    return logger
+logger = setup_logging('utils/logging.json')
+
 
 app = Flask(__name__)
 app.use_reloader=False
@@ -34,7 +51,7 @@ class Predictor(object):
     def __init__(self, args):
         self.args = args
         self.args.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        print(self.args.device)
+        #print(self.args.device)
         self.args.nprocs = torch.cuda.device_count()
         self.cls_dict = {}
         self.num_classes = 0
@@ -49,7 +66,7 @@ class Predictor(object):
         config.split = self.args.split
         config.slide_step = self.args.slide_step
         model_name = os.path.basename(self.args.pretrained_model).replace("_checkpoint.bin", "")
-        print("use model_name: ", model_name)
+        #print("use model_name: ", model_name)
         self.num_classes = 5
         self.cls_dict = {0: "noemp", 1: "yesemp", 2: "hard", 3: "fly", 4: "stack"}
         self.model = VisionTransformer(config, self.args.img_size, zero_head=True, num_classes=self.num_classes, smoothing_value=self.args.smoothing_value)
@@ -67,7 +84,8 @@ class Predictor(object):
     def normal_predict(self, img_data, result):
         # img = Image.open(img_path)
         if img_data is None:
-            print('error, img data is None')
+            #print('error, img data is None')
+            logger.warning('error, img data is None')
             return result
         else:
             with torch.no_grad():
@@ -79,7 +97,7 @@ class Predictor(object):
                 topN = torch.argsort(probs, dim=-1, descending=True).tolist()
                 clas_ids = topN[0][0]
                 clas_ids = 0 if 0==int(clas_ids) or 2 == int(clas_ids) or 3 == int(clas_ids) else 1
-                print("cur_img result: class id: %d, score: %0.3f" % (clas_ids, probs[0, clas_ids].item()))
+                #print("cur_img result: class id: %d, score: %0.3f" % (clas_ids, probs[0, clas_ids].item()))
                 result["success"] = "true"
                 result["rst_cls"] = str(clas_ids)
                 return result
@@ -94,14 +112,15 @@ predictor = Predictor(args)
 @app.route("/isempty", methods=['POST'])
 def get_isempty():
     start = time.time()
-    print('--------------------EmptyPredict-----------------')
+    #print('--------------------EmptyPredict-----------------')
     data = request.get_data()
     ip = request.remote_addr
-    print('------ ip = %s ------' % ip)
+    #print('------ ip = %s ------' % ip)
+    logger.info(ip)
 
     json_data = json.loads(data.decode("utf-8"))
     getdateend = time.time()
-    print('get date use time: {0:.2f}s'.format(getdateend - start))
+    #print('get date use time: {0:.2f}s'.format(getdateend - start))
 
     pic = json_data.get("pic")
     result = {"success": "false",
@@ -113,29 +132,11 @@ def get_isempty():
         img_src = cv2.imdecode(imgdata_np, cv2.IMREAD_COLOR)
         img_data = Image.fromarray(np.uint8(img_src))
         result = predictor.normal_predict(img_data, result)  # 1==empty, 0==nonEmpty
-    except:
+    except Exception as e:
+        logger.warning(e)
         return repr(result)
-
+    logger.info(repr(result))
     return repr(result)
 
-
 if __name__ == "__main__":
-    app.run()
-#    http_server = WSGIServer(('0.0.0.0',8000), app)
-#    http_server.serve_forever()
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+    app.run(host='192.168.1.142', port=8000)