31 lines
3.5 KiB
Plaintext
31 lines
3.5 KiB
Plaintext
|
Ë
|
|||
|
|
>û gŸ ã ó” — d dl mZmZmZ d dlmZmZmZmZm Z m
|
|||
|
|
Z
|
|||
|
|
m Z m Z m
|
|||
|
|
Z
|
|||
|
|
mZmZmZmZ d dlmZmZ ddlmZ ddlmZ ddlmZ ej4 d « dd eeef fd „« Z ej4 d
|
|||
|
|
« de d eeef fd„« Z ej< d« deee ee f deeef deeef d eeee ef ef fd„« Z y
|
|||
|
|
)é )ÚListÚTupleÚcast)
|
|||
|
|
ÚLinearÚLogisticÚMaxoutÚModelÚchainÚ concatenateÚglorot_uniform_initÚ list2raggedÚ reduce_firstÚ reduce_lastÚ
|
|||
|
|
reduce_maxÚ reduce_meanÚ with_getitem)ÚFloats2dÚRaggedé )ÚDoc)Úregistryé )Ú
|
|||
|
|
extract_spanszspacy.LinearLogistic.v1NÚreturnc óJ — t t | |t ¬« t « « S )zrAn output layer for multi-label classification. It uses a linear layer
|
|||
|
|
followed by a logistic activation.
|
|||
|
|
)ÚnOÚnIÚinit_W)r
|
|||
|
|
r r r )r r s úXC:\Users\garci\AppData\Roaming\Python\Python312\site-packages\spacy/ml/models/spancat.pyÚbuild_linear_logisticr s € ô
|
|||
|
|
”˜2 "Ô-@ÔAÄ8Ã:Ó NÐNó zspacy.mean_max_reducer.v1Ú hidden_sizec
|
|||
|
|
óö — t t t t t t
|
|||
|
|
f t
|
|||
|
|
« « t t t t
|
|||
|
|
f t « « t « t « « t | dd¬« « S )zŒReduce sequences by concatenating their mean and max pooled vectors,
|
|||
|
|
and then combine the concatenated vectors with a hidden layer.
|
|||
|
|
Tg )r Ú normalizeÚdropout) r
|
|||
|
|
r r r r r r r r r r )r" s r Úbuild_mean_max_reducerr& ! s] € ô
|
|||
|
|
ÜÜ ””vœxÐ'Ñ(¬+«-Ó 8Ü ””vœxÐ'Ñ(¬,«.Ó 9Ü ‹MÜ ‹Ló
|
|||
|
|
ô �+¨°sÔ;ó ð r! zspacy.SpanCategorizer.v1Útok2vecÚreducerÚscorerc ó’ — t t t t t t
|
|||
|
|
t f t t t f f t dt | t t t t t f t « « « « « t « ||« }|j d| « |j d|« |j d|« |S )a‘ Build a span categorizer model, given a token-to-vector model, a
|
|||
|
|
reducer model to map the sequence of vectors for each span down to a single
|
|||
|
|
vector, and a scorer model to map the vectors to probabilities.
|
|||
|
|
|
|||
|
|
tok2vec (Model[List[Doc], List[Floats2d]]): The tok2vec model.
|
|||
|
|
reducer (Model[Ragged, Floats2d]): The reducer model.
|
|||
|
|
scorer (Model[Floats2d, Floats2d]): The scorer model.
|