artline-demo Can't get attribute 'FeatureLoss' on <module '__main_

Thank you very much for your resources. In Linux environment, Uwsgi deployment, error still occurs: ** Starting uWSGI 2.0.19.1 (64bit) on [Thu Dec 31 18:07:43 2020] *** compiled with version: 5.4.0 20160609 on 17 December 2020 08:16:00 os: Linux-4.4.0-198-generic #230-Ubuntu SMP Sat Nov 28 01:30:29 UTC 2020 nodename: 10-9-60-142 machine: x86_64 clock source: unix pcre jit disabled detected number of CPU cores: 4 current working directory: /home/ubuntu/chengping/artline-demo-main writing pidfile to uwsgi.pid detected binary path: /home/ubuntu/songcheng/venv3.0/bin/uwsgi uWSGI running as root, you can use --uid/--gid/--chroot options *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** chdir() to /home/ubuntu/chengping/artline-demo-main/ your processes number limit is 63944 your memory page size is 4096 bytes detected max file descriptor number: 1000000 lock engine: pthread robust mutexes thunder lock: disabled (you can enable it with --thunder-lock) uwsgi socket 0 bound to TCP address 0.0.0.0:5000 fd 3 uWSGI running as root, you can use --uid/--gid/--chroot options *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** Python version: 3.7.1 (default, Dec 17 2020, 15:23:31) [GCC 5.4.0 20160609] Set PythonHome to /home/ubuntu/songcheng/venv3.0/ Python main interpreter initialized at 0xc51680 uWSGI running as root, you can use --uid/--gid/--chroot options *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** python threads support enabled your server socket listen backlog is limited to 100 connections your mercy for graceful operations on workers is 60 seconds mapped 145840 bytes (142 KB) for 1 cores *** Operational MODE: single process *** uWSGI running as root, you can use --uid/--gid/--chroot options *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** *** uWSGI is running in multiple interpreter mode *** spawned uWSGI master process (pid: 14225) spawned uWSGI worker 1 (pid: 14226, cores: 1) *** Stats server enabled on 0.0.0.0:8383 fd: 9 *** Traceback (most recent call last): File "./app_cpu.py", line 76, in state = torch.load('ArtLine_650.pkl', map_location='cpu') if defaults.device == torch.device('cpu') else torch.load(source) File "/home/ubuntu/venv3.0/lib/python3.7/site-packages/torch/serialization.py", line 584, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/home/ubuntu/venv3.0/lib/python3.7/site-packages/torch/serialization.py", line 842, in _load result = unpickler.load() AttributeError: Can't get attribute 'FeatureLoss' on <module 'main' (built-in)> unable to load app 0 (mountpoint='') (callable not found or import error) *** no app loaded. going in full dynamic mode ***

but, In the same situation, I can run my service in Python.