mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
06f0a8daa0
* fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
30 lines
1010 B
Python
30 lines
1010 B
Python
from thinc.api import chain, Maxout, LayerNorm, Softmax, Linear, zero_init
|
|
|
|
|
|
def build_multi_task_model(n_tags, tok2vec=None, token_vector_width=96):
|
|
model = chain(
|
|
tok2vec,
|
|
Maxout(nO=token_vector_width * 2, nI=token_vector_width, nP=3, dropout=0.0),
|
|
LayerNorm(token_vector_width * 2),
|
|
Softmax(nO=n_tags, nI=token_vector_width * 2),
|
|
)
|
|
return model
|
|
|
|
|
|
def build_cloze_multi_task_model(vocab, tok2vec):
|
|
output_size = vocab.vectors.data.shape[1]
|
|
output_layer = chain(
|
|
Maxout(
|
|
nO=output_size, nI=tok2vec.get_dim("nO"), nP=3, normalize=True, dropout=0.0
|
|
),
|
|
Linear(nO=output_size, nI=output_size, init_W=zero_init),
|
|
)
|
|
model = chain(tok2vec, output_layer)
|
|
model = build_masked_language_model(vocab, model)
|
|
return model
|
|
|
|
|
|
def build_masked_language_model(*args, **kwargs):
|
|
# TODO cf https://github.com/explosion/spaCy/blob/2c107f02a4d60bda2440db0aad1a88cbbf4fb52d/spacy/_ml.py#L828
|
|
raise NotImplementedError
|