View Single Post
Old 12-05-2022, 06:48 PM   #515
xxyzz
Evangelist
xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.xxyzz ought to be getting tired of karma fortunes by now.
 
Posts: 442
Karma: 2666666
Join Date: Nov 2020
Device: none
Maybe spaCy finds some new X-Ray entities with GPU model and queries them on Wikipedia API takes some time at the first time, create X-Ray for the same book later would use a Wikipedia cache file.

Memory usage could also be a factor. I don't know how much RAM(system and GPU RAM) spaCy GPU model would use, but I guess 6G should be enough.

And spaCy doc says the GPU model has higher NER accuracy, do you think the X-Ray file get better?

Last edited by xxyzz; 12-05-2022 at 07:14 PM.
xxyzz is offline   Reply With Quote