mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-01 04:46:38 +03:00
5e297aa20e
* 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> |
||
---|---|---|
.. | ||
architectures.mdx | ||
attributeruler.mdx | ||
attributes.mdx | ||
cli.mdx | ||
coref.mdx | ||
corpus.mdx | ||
cython-classes.mdx | ||
cython-structs.mdx | ||
cython.mdx | ||
data-formats.mdx | ||
dependencymatcher.mdx | ||
dependencyparser.mdx | ||
doc.mdx | ||
docbin.mdx | ||
edittreelemmatizer.mdx | ||
entitylinker.mdx | ||
entityrecognizer.mdx | ||
entityruler.mdx | ||
example.mdx | ||
index.mdx | ||
kb_in_memory.mdx | ||
kb.mdx | ||
language.mdx | ||
legacy.mdx | ||
lemmatizer.mdx | ||
lexeme.mdx | ||
lookups.mdx | ||
matcher.mdx | ||
morphologizer.mdx | ||
morphology.mdx | ||
phrasematcher.mdx | ||
pipe.mdx | ||
pipeline-functions.mdx | ||
scorer.mdx | ||
sentencerecognizer.mdx | ||
sentencizer.mdx | ||
span-resolver.mdx | ||
span.mdx | ||
spancategorizer.mdx | ||
spangroup.mdx | ||
spanruler.mdx | ||
stringstore.mdx | ||
tagger.mdx | ||
textcategorizer.mdx | ||
tok2vec.mdx | ||
token.mdx | ||
tokenizer.mdx | ||
top-level.mdx | ||
transformer.mdx | ||
vectors.mdx | ||
vocab.mdx |