search

ShannonAI / service-streamer

Boosting your Web Services of Deep Learning Applications.
Apache License 2.0
1.22k stars 187 forks source link

TypeError: can't pickle _thread.RLock objects #69

Open c0derm4n opened 4 years ago

c0derm4n commented 4 years ago

File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/advanced_deploy_api.py", line 76, in streamer = Streamer(model.predict, batch_size=8, max_latency=0.1, worker_num=1) File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/service_streamer.py", line 296, in init self._setup_gpu_worker() File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/service_streamer.py", line 311, in _setup_gpu_worker p.start() File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/process.py", line 105, in start self._popen = self._Popen(self) File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/context.py", line 284, in _Popen return Popen(process_obj) File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 32, in init super().init(process_obj) File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/popen_fork.py", line 19, in init self._launch(process_obj) File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 47, in _launch reduction.dump(process_obj, fp) File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) TypeError: can't pickle _thread.RLock objects

yjiangling commented 4 years ago

@Meteorix @pku-wuwei Same Error, please give some help, thanks a lot!

Traceback (most recent call last): File "asr_api.py", line 92, in streamer=Streamer(model.predict,batch_size=4,max_latency=0.01) File "/media/huaxin/tcl1/asr/yujiangling/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 267, in init self._setup_gpu_worker() File "/media/huaxin/tcl1/asr/yujiangling/lib/python3.6/site-packages/service_streamer/service_streamer.py", line 280, in _setup_gpu_worker p.start() File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/process.py", line 105, in start self._popen = self._Popen(self) File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/context.py", line 284, in _Popen return Popen(process_obj) File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 32, in init super().init(process_obj) File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/popen_fork.py", line 19, in init self._launch(process_obj) File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/popen_spawn_posix.py", line 47, in _launch reduction.dump(process_obj, fp) File "/media/huaxin/tcl1/asr/anaconda3/lib/python3.6/multiprocessing/reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) TypeError: can't pickle LockType objects