explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-29 17:33:10 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Use openmp in parser

Browse Source
This commit is contained in:
Matthew Honnibal 2016-02-01 03:08:42 +01:00
parent 9c34ca9e5d
commit 490ba65398
2 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
setup.py
View File

@ -71,9 +71,9 @@ if sys.version_info[:2] < (2, 7) or (3, 0) <= sys.version_info[0:2] < (3, 4):
# By subclassing build_extensions we have the actual compiler that will be used which is really known only after finalize_options # By subclassing build_extensions we have the actual compiler that will be used which is really known only after finalize_options
# http://stackoverflow.com/questions/724664/python-distutils-how-to-get-a-compiler-that-is-going-to-be-used # http://stackoverflow.com/questions/724664/python-distutils-how-to-get-a-compiler-that-is-going-to-be-used
compile_options = {'msvc' : ['/Ox', '/EHsc'], compile_options = {'msvc' : ['/Ox', '/EHsc'],
'other' : ['-O3', '-Wno-strict-prototypes', '-Wno-unused-function']} 'other' : ['-O3', '-Wno-strict-prototypes', '-Wno-unused-function', '-fopenmp']}
link_options = {'msvc' : [], link_options = {'msvc' : [],
'other' : []} 'other' : ['-fopenmp']}
if sys.platform.startswith('darwin'): if sys.platform.startswith('darwin'):
compile_options['other'].append('-mmacosx-version-min=10.8') compile_options['other'].append('-mmacosx-version-min=10.8')

18
spacy/syntax/parser.pyx
View File

@ -21,6 +21,10 @@ from murmurhash.mrmr cimport hash64
from thinc.typedefs cimport weight_t, class_t, feat_t, atom_t, hash_t from thinc.typedefs cimport weight_t, class_t, feat_t, atom_t, hash_t
from thinc.linear.avgtron cimport AveragedPerceptron from thinc.linear.avgtron cimport AveragedPerceptron
from thinc.linalg cimport VecVec from thinc.linalg cimport VecVec
from thinc.structs cimport SparseArrayC
from thinc.structs cimport FeatureC
from preshed.maps cimport MapStruct
from preshed.maps cimport map_get
from util import Config from util import Config
@ -101,7 +105,6 @@ cdef class Parser:
def __call__(self, Doc tokens): def __call__(self, Doc tokens):
cdef StateClass stcls = StateClass.init(tokens.c, tokens.length) cdef StateClass stcls = StateClass.init(tokens.c, tokens.length)
self.moves.initialize_state(stcls) self.moves.initialize_state(stcls)
cdef Example eg = Example( cdef Example eg = Example(
nr_class=self.moves.n_moves, nr_class=self.moves.n_moves,
nr_atom=CONTEXT_SIZE, nr_atom=CONTEXT_SIZE,
@ -112,13 +115,22 @@ cdef class Parser:
PyErr_CheckSignals() PyErr_CheckSignals()
cdef void parseC(self, Doc tokens, StateClass stcls, Example eg) nogil: cdef void parseC(self, Doc tokens, StateClass stcls, Example eg) nogil:
cdef const MapStruct* weights_table = self.model.weights.c_map
cdef int i, j
cdef FeatureC feat
while not stcls.is_final(): while not stcls.is_final():
self.model.set_featuresC(&eg.c, stcls) self.model.set_featuresC(&eg.c, stcls)
self.moves.set_valid(eg.c.is_valid, stcls.c) self.moves.set_valid(eg.c.is_valid, stcls.c)
self.model.set_scoresC(eg.c.scores, eg.c.features, eg.c.nr_feat) self.model.set_scoresC(eg.c.scores, eg.c.features, eg.c.nr_feat)
for i in range(eg.c.nr_feat):
feat = eg.c.features[i]
class_weights = <const SparseArrayC*>map_get(weights_table, feat.key)
if class_weights != NULL:
j = 0
while class_weights[j].key >= 0:
eg.c.scores[class_weights[j].key] += class_weights[j].val * feat.value
j += 1
guess = VecVec.arg_max_if_true(eg.c.scores, eg.c.is_valid, eg.c.nr_class) guess = VecVec.arg_max_if_true(eg.c.scores, eg.c.is_valid, eg.c.nr_class)
action = self.moves.c[guess] action = self.moves.c[guess]
if not eg.c.is_valid[guess]: if not eg.c.is_valid[guess]:
with gil: with gil: