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
..
__init__.py	Tidy up code	2021-06-28 12:08:15 +02:00
entity_linker.py	Fix entity linker batching (#9669)	2022-03-04 09:17:36 +01:00
multi_task.py	Auto-format code with black (#10209)	2022-02-06 16:30:30 +01:00
parser.py	Replace use_ops("numpy") by use_ops("cpu") in the parser (#9501)	2021-10-21 11:22:45 +02:00
spancat.py	🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)	2021-10-14 15:21:40 +02:00
tagger.py	Tagger: use unnormalized probabilities for inference (#10197)	2022-03-15 14:15:31 +01:00
textcat.py	🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)	2021-10-14 15:21:40 +02:00
tok2vec.py	MultiHashEmbed vector docs correction (#9918)	2021-12-27 11:18:08 +01:00