explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Restore optimized hidden_depth=0 for parser

Browse Source
This commit is contained in:
Matthew Honnibal 2017-08-21 19:18:04 -05:00
parent c10f63bf10
commit 682346dd66
2 changed files with 55 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/syntax/nn_parser.pxd
View File

@ -14,4 +14,8 @@ cdef class Parser:
cdef readonly TransitionSystem moves
cdef readonly object cfg
cdef void _parse_step(self, StateC* state,
const float* feat_weights,
int nr_class, int nr_feat, int nr_piece) nogil
#cdef int parseC(self, TokenC* tokens, int length, int nr_feat) nogil

34
spacy/syntax/nn_parser.pyx
View File

@ -257,10 +257,15 @@ cdef class Parser:
nI=token_vector_width)
with Model.use_device('cpu'):
if depth == 0:
upper = chain()
upper.is_noop = True
else:
upper = chain(
clone(Maxout(hidden_width), (depth-1)),
zero_init(Affine(nr_class, drop_factor=0.0))
)
upper.is_noop = False
# TODO: This is an unfortunate hack atm!
# Used to set input dimensions in network.
lower.begin_training(lower.ops.allocate((500, token_vector_width)))
@ -412,7 +417,14 @@ cdef class Parser:
cdef np.ndarray scores
c_token_ids = <int*>token_ids.data
c_is_valid = <int*>is_valid.data
cdef int has_hidden = not getattr(vec2scores, 'is_noop', False)
while not next_step.empty():
if not has_hidden:
for i in cython.parallel.prange(
next_step.size(), num_threads=6, nogil=True):
self._parse_step(next_step[i],
feat_weights, nr_class, nr_feat, nr_piece)
else:
for i in range(next_step.size()):
st = next_step[i]
st.set_context_tokens(&c_token_ids[i*nr_feat], nr_feat)
@ -482,6 +494,28 @@ cdef class Parser:
beams.append(beam)
return beams
cdef void _parse_step(self, StateC* state,
const float* feat_weights,
int nr_class, int nr_feat, int nr_piece) nogil:
'''This only works with no hidden layers -- fast but inaccurate'''
#for i in cython.parallel.prange(next_step.size(), num_threads=4, nogil=True):
# self._parse_step(next_step[i], feat_weights, nr_class, nr_feat)
token_ids = <int*>calloc(nr_feat, sizeof(int))
scores = <float*>calloc(nr_class * nr_piece, sizeof(float))
is_valid = <int*>calloc(nr_class, sizeof(int))
state.set_context_tokens(token_ids, nr_feat)
sum_state_features(scores,
feat_weights, token_ids, 1, nr_feat, nr_class * nr_piece)
self.moves.set_valid(is_valid, state)
guess = arg_maxout_if_valid(scores, is_valid, nr_class, nr_piece)
action = self.moves.c[guess]
action.do(state, action.label)
free(is_valid)
free(scores)
free(token_ids)
def update(self, docs_tokvecs, golds, drop=0., sgd=None, losses=None):
if not any(self.moves.has_gold(gold) for gold in golds):
return None