mirror of
https://github.com/explosion/spaCy.git
synced 2025-03-04 11:25:51 +03:00
* Add `TrainablePipe.{distill,get_teacher_student_loss}` This change adds two methods: - `TrainablePipe::distill` which performs a training step of a student pipe on a teacher pipe, giving a batch of `Doc`s. - `TrainablePipe::get_teacher_student_loss` computes the loss of a student relative to the teacher. The `distill` or `get_teacher_student_loss` methods are also implemented in the tagger, edit tree lemmatizer, and parser pipes, to enable distillation in those pipes and as an example for other pipes. * Fix stray `Beam` import * Fix incorrect import * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * TrainablePipe.distill: use `Iterable[Example]` * Add Pipe.is_distillable method * Add `validate_distillation_examples` This first calls `validate_examples` and then checks that the student/teacher tokens are the same. * Update distill documentation * Add distill documentation for all pipes that support distillation * Fix incorrect identifier * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Add comment to explain `is_distillable` Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> |
||
---|---|---|
.. | ||
_edit_tree_internals | ||
_parser_internals | ||
legacy | ||
__init__.py | ||
attribute_ruler.py | ||
dep_parser.pyx | ||
edit_tree_lemmatizer.py | ||
entity_linker.py | ||
entityruler.py | ||
functions.py | ||
lemmatizer.py | ||
morphologizer.pyx | ||
ner.pyx | ||
pipe.pxd | ||
pipe.pyi | ||
pipe.pyx | ||
sentencizer.pyx | ||
senter.pyx | ||
span_ruler.py | ||
spancat.py | ||
tagger.pyx | ||
textcat_multilabel.py | ||
textcat.py | ||
tok2vec.py | ||
trainable_pipe.pxd | ||
trainable_pipe.pyx | ||
transition_parser.pxd | ||
transition_parser.pyx |