又叕又碰到这个多进程问题了，其实线程也行，下面再次进行demo测试
召回中遇到的，存储召回的items
For Video Recommendation in Deep learning QQ Group 277356808
For Visual in deep learning QQ Group 629530787
I'm here waiting for you
wanna have a date with someone in Beijing please join in the QQ Group 737813700
from multiprocessing import Process,Pool
Pool(32)与Pool(64)相比没有慢多少，一个是116s，一个是90s，因此保险考虑32为好
遇到一个问题：多进程Pool中
AttributeError: Can't pickle local object 'update_model.<locals>.delete_copy_items'
下面小demo复现
Traceback (most recent call last):
File "multiprocess_Process_Pool_.py", line 99, in
