Entity-Recognition-In-Resumes-SpaCy icon indicating copy to clipboard operation
Entity-Recognition-In-Resumes-SpaCy copied to clipboard

How can export and use the trained model ?

Open asriabdelhakim opened this issue 5 years ago • 5 comments

Hello; I just trained my model with my data, so i want to export my model and use it back later with data. Thank you :)

asriabdelhakim avatar Mar 24 '19 01:03 asriabdelhakim

Hi @mrfast7, You can do that by using the following two commands:

nlp.to_disk('my_model') nlp1 = spacy.load('my_model')

All model related files get stored in this directory 'my_model'.

drishyamlabs avatar Apr 25 '19 11:04 drishyamlabs

Please can you suggest me an open source and free annotation tool ? Thank you

Le jeu. 25 avr. 2019 à 12:55, Saahil Gupta [email protected] a écrit :

Hi @mrfast7 https://github.com/mrfast7, You can do that by using the following two commands:

nlp.to_disk('my_model') nlp1 = spacy.load('my_model')

All model related files get stored in this directory 'my_model'.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/DataTurks-Engg/Entity-Recognition-In-Resumes-SpaCy/issues/8#issuecomment-486641545, or mute the thread https://github.com/notifications/unsubscribe-auth/ALRHOWHBS5QEFI6SSAF377DPSGL4BANCNFSM4HAVAE5Q .

asriabdelhakim avatar Apr 25 '19 12:04 asriabdelhakim

@mrfast7 I think this repo will help https://github.com/ManivannanMurugavel/spacy-ner-annotator

Abhimanyu100 avatar Nov 08 '19 05:11 Abhimanyu100

@saahilgupta93 I am using your two line code to save my NER Spacy model it's throwing this error Namerror: name 'nlp' is not defined Here is my code. https://pastebin.com/ySVTSLMG

Abhimanyu100 avatar Nov 12 '19 09:11 Abhimanyu100

Hi @mrfast7, You can do that by using the following two commands:

nlp.to_disk('my_model') nlp1 = spacy.load('my_model')

All model related files get stored in this directory 'my_model'.

@saahilgupta93 I am using this but getting wrong results after saving and loading model. But when I use the trained model directly, I am getting correct results. Any idea why?

sayalraza avatar Dec 03 '19 07:12 sayalraza