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()
+    app.run(host='192.168.1.142', port=8000)
-#    http_server = WSGIServer(('0.0.0.0',8000), app)
-#    http_server.serve_forever()
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

train.py

@@ -20,10 +20,11 @@ from models.modeling import VisionTransformer, CONFIGS
 from utils.scheduler import WarmupLinearSchedule, WarmupCosineSchedule
 from utils.data_utils import get_loader
 from utils.dist_util import get_world_size
+import pdb
 
 logger = logging.getLogger(__name__)
 
-
+os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2"
 class AverageMeter(object):
     """Computes and stores the average and current value"""
     def __init__(self):
@@ -92,12 +93,14 @@ def setup(args):
     if args.pretrained_model is not None:
         pretrained_model = torch.load(args.pretrained_model)['model']
         model.load_state_dict(pretrained_model)
-    model.to(args.device)
+    #model.to(args.device)
+    #pdb.set_trace()
     num_params = count_parameters(model)
 
     logger.info("{}".format(config))
     logger.info("Training parameters %s", args)
     logger.info("Total Parameter: \t%2.1fM" % num_params)
+    model = torch.nn.DataParallel(model, device_ids=[0,1]).cuda()
     return args, model
 
 
@@ -351,6 +354,7 @@ def main():
         device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
         print('torch.cuda.device_count()>>>>>>>>>>>>>>>>>>>>>>>>>', torch.cuda.device_count())
         args.n_gpu = torch.cuda.device_count()
+        print('torch.cuda.device_count()>>>>>>>>>>>>>>>>>>>>>>>>>', torch.cuda.device_count()) 
     else:  # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
         torch.cuda.set_device(args.local_rank)
         device = torch.device("cuda", args.local_rank)

utils/logging.json

@@ -0,0 +1,46 @@
+{
+    "version":1,
+    "disable_existing_loggers":false,
+    "formatters":{
+        "simple":{
+            "format":"%(asctime)s - %(module)s - %(thread)d - %(levelname)s : %(message)s"
+        }
+    },
+    "handlers":{
+        "console":{
+            "class":"logging.StreamHandler",
+            "level":"DEBUG",
+            "formatter":"simple",
+            "stream":"ext://sys.stdout"
+        },
+        "info_file_handler":{
+            "class":"logging.handlers.RotatingFileHandler",
+            "level":"INFO",
+            "formatter":"simple",
+            "filename":"../log/ieemoo-ai-isempty-biz.log",
+            "maxBytes":10485760,
+            "backupCount":20,
+            "encoding":"utf8"
+        },
+        "error_file_handler":{
+            "class":"logging.handlers.RotatingFileHandler",
+            "level":"ERROR",
+            "formatter":"simple",
+            "filename":"../log/ieemoo-ai-isempty-biz.log",
+            "maxBytes":10485760,
+            "backupCount":20,
+            "encoding":"utf8"
+        }
+    },
+    "loggers":{
+            "my_module":{
+                    "level":"ERROR",
+                    "handlers":["info_file_handler"],
+                    "propagate":"no"}
+    },
+    "root":{
+            "level":"INFO",
+            "handlers":["console","info_file_handler","error_file_handler"]
+    }
+}
+