mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-26 05:31:15 +03:00
* 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 |
||
|---|---|---|
| .. | ||
| project | ||
| templates | ||
| __init__.py | ||
| _util.py | ||
| assemble.py | ||
| convert.py | ||
| debug_config.py | ||
| debug_data.py | ||
| debug_model.py | ||
| download.py | ||
| evaluate.py | ||
| info.py | ||
| init_config.py | ||
| init_pipeline.py | ||
| package.py | ||
| pretrain.py | ||
| profile.py | ||
| train.py | ||
| validate.py | ||