cvat: Detection error occurred Error: Request failed with status code 503. "HTTPConnectionPool(host='host.docker.internal', port=32938): Max retries exceeded with url: / (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 111] Connection refused'))".

I tried to deploy an automatic annotation function with the YOLOv5 model that I trained myself. I made modifications to the function-gpu.yaml and main.py files.

Here are the changes: for main.py model = torch.hub.load('ultralytics/yolov5', 'yolov5s') to model = torch.hub.load('/home/being/Disk_2T/kyle_work/yolov5-v6.0-haice', 'custom', '/home/being/Disk_2T/kyle_work/yolov5-v6.0-haice/runs/train/exp78-20230518best/weights/best.pt', source='local') for function-gpu.yaml, changed spec to spec: | [ { "id": 0, "name": "40_covered" }, { "id": 1, "name": "40_uncovered" }, { "id": 2, "name": "20_covered" }, { "id": 3, "name": "20_uncovered" } ]

Then, I ran the command: ./deploy_gpu.sh serverless/pytorch/haice/yolov5/nuclio to activate the model.

However, when I tried to use the automatic annotation in CVAT, I encountered the following error: Detection error occurred Error: Request failed with status code 503. “HTTPConnectionPool(host=‘host.docker.internal’, port=32938): Max retries exceeded with url: / (Caused by NewConnectionError(‘<urllib3.connection.HTTPConnection object at 0x7fe2d8806c50>: Failed to establish a new connection: [Errno 111] Connection refused’))”.

docker logs:

23.06.02 07:32:20.520 cessor.healthcheck.server (I) Listening {“listenAddress”: “:8082”} 23.06.02 07:32:20.520 processor.http (D) Creating worker pool {“num”: 1} 23.06.02 07:32:20.520 sor.http.w0.python.logger (D) Creating listener socket {“path”: “/tmp/nuclio-rpc-chspm12r86jtblth86c0.sock”} 23.06.02 07:32:20.521 sor.http.w0.python.logger (W) Python 3.6 runtime is deprecated and will soon not be supported. Please migrate your code and use Python 3.7 runtime (python:3.7) or higher 23.06.02 07:32:20.521 sor.http.w0.python.logger (D) Using Python wrapper script path {“path”: “/opt/nuclio/_nuclio_wrapper.py”} 23.06.02 07:32:20.521 sor.http.w0.python.logger (D) Using Python handler {“handler”: “main:handler”} 23.06.02 07:32:20.521 sor.http.w0.python.logger (D) Using Python executable {“path”: “/opt/conda/bin/python3”} 23.06.02 07:32:20.521 sor.http.w0.python.logger (D) Setting PYTHONPATH {“value”: “PYTHONPATH=/opt/nuclio”} 23.06.02 07:32:20.521 sor.http.w0.python.logger (D) Running wrapper {“command”: “/opt/conda/bin/python3 -u /opt/nuclio/_nuclio_wrapper.py --handler main:handler --socket-path /tmp/nuclio-rpc-chspm12r86jtblth86c0.sock --platform-kind local --namespace nuclio --worker-id 0 --trigger-kind http --trigger-name myHttpTrigger --decode-event-strings”} /opt/nuclio/_nuclio_wrapper.py:395: DeprecationWarning: There is no current event loop loop = asyncio.get_event_loop() 23.06.02 07:32:22.428 sor.http.w0.python.logger (I) Wrapper connected {“wid”: 0, “pid”: 20} 23.06.02 07:32:22.429 sor.http.w0.python.logger (D) Waiting for start {“datetime”: “2023-06-02 07:32:22,429”, “level”: “info”, “message”: “Replacing logger output”, “with”: {“handler_name”: “default”, “worker_id”: “0”}} 23.06.02 07:32:22.429 sor.http.w0.python.logger (I) Init context… 0% {“worker_id”: “0”} 23.06.02 07:32:22.430 sor.http.w0.python.logger (E) Exception raised while running init_context {“worker_id”: “0”} Traceback (most recent call last): File “/opt/nuclio/_nuclio_wrapper.py”, line 432, in <module> run_wrapper() File “/opt/nuclio/_nuclio_wrapper.py”, line 420, in run_wrapper loop.run_until_complete(wrapper_instance.initialize()) File “/opt/conda/lib/python3.10/asyncio/base_events.py”, line 649, in run_until_complete return future.result() File “/opt/nuclio/_nuclio_wrapper.py”, line 147, in initialize await self._initialize_context() File “/opt/nuclio/_nuclio_wrapper.py”, line 158, in _initialize_context init_context_result = getattr(self._entrypoint_module, ‘init_context’)(self._context) File “/opt/nuclio/main.py”, line 12, in init_context model = torch.hub.load(‘/home/being/Disk_2T/kyle_work/yolov5-v6.0-haice’,‘custom’, ‘/home/being/Disk_4T/cvat/serverless/pytorch/haice/yolov5/nuclio/best.pt’,source=‘local’,force_reload=True) # or yolov5m, yolov5l, yolov5x, custom File “/opt/conda/lib/python3.10/site-packages/torch/hub.py”, line 558, in load model = _load_local(repo_or_dir, model, *args, **kwargs) File “/opt/conda/lib/python3.10/site-packages/torch/hub.py”, line 584, in _load_local hub_module = _import_module(MODULE_HUBCONF, hubconf_path) File “/opt/conda/lib/python3.10/site-packages/torch/hub.py”, line 98, in _import_module spec.loader.exec_module(module) File “<frozen importlib._bootstrap_external>”, line 879, in exec_module File “<frozen importlib._bootstrap_external>”, line 1016, in get_code File “<frozen importlib._bootstrap_external>”, line 1073, in get_data FileNotFoundError: [Errno 2] No such file or directory: ‘/home/being/Disk_2T/kyle_work/yolov5-v6.0-haice/hubconf.py’ 23.06.02 07:32:22.972 sor.http.w0.python.logger (W) Failed to read from connection {“err”: “EOF”} 23.06.02 07:32:22.972 sor.http.w0.python.logger (E) Unexpected termination of child process {“error”: null, “status”: “exit status 1”} panic: Wrapper process for worker 0 exited unexpectedly with: exit status 1

goroutine 59 [running]: github.com/nuclio/nuclio/pkg/processor/runtime/rpc.(*AbstractRuntime).watchWrapperProcess(0xc000378cc0) /nuclio/pkg/processor/runtime/rpc/abstract.go:471 +0x445 created by github.com/nuclio/nuclio/pkg/processor/runtime/rpc.(*AbstractRuntime).startWrapper /nuclio/pkg/processor/runtime/rpc/abstract.go:244 +0x1c5

Could anyone help me with this?