3 Commits

Author	SHA1	Message	Date
Daniël de Kok	e5debc68e4	Tagger: use unnormalized probabilities for inference (#10197) ... * Tagger: use unnormalized probabilities for inference Using unnormalized softmax avoids use of the relatively expensive exp function, which can significantly speed up non-transformer models (e.g. I got a speedup of 27% on a German tagging + parsing pipeline). * Add spacy.Tagger.v2 with configurable normalization Normalization of probabilities is disabled by default to improve performance. * Update documentation, models, and tests to spacy.Tagger.v2 * Move Tagger.v1 to spacy-legacy * docs/architectures: run prettier * Unnormalized softmax is now a Softmax_v2 option * Require thinc 8.0.14 and spacy-legacy 3.0.9	2022-03-15 14:15:31 +01:00
Adriane Boyd	5eeb25f043	Tidy up code	2021-06-28 12:08:15 +02:00
Sofie Van Landeghem	cd70c3cb79	Fixing pretrain (#7342) ... * initialize NLP with train corpus * add more pretraining tests * more tests * function to fetch tok2vec layer for pretraining * clarify parameter name * test different objectives * formatting * fix check for static vectors when using vectors objective * clarify docs * logger statement * fix init_tok2vec and proc.initialize order * test training after pretraining * add init_config tests for pretraining * pop pretraining block to avoid config validation errors * custom errors	2021-03-09 14:01:13 +11:00