mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
e5debc68e4
* 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 |
||
---|---|---|
.. | ||
__init__.py | ||
test_analysis.py | ||
test_annotates_on_update.py | ||
test_attributeruler.py | ||
test_entity_linker.py | ||
test_entity_ruler.py | ||
test_functions.py | ||
test_initialize.py | ||
test_lemmatizer.py | ||
test_models.py | ||
test_morphologizer.py | ||
test_pipe_factories.py | ||
test_pipe_methods.py | ||
test_sentencizer.py | ||
test_senter.py | ||
test_spancat.py | ||
test_tagger.py | ||
test_textcat.py | ||
test_tok2vec.py |