def my_parser():
tok2vec = build_Tok2Vec_model(
MultiHashEmbed(
width=321,
attrs=["LOWER", "SHAPE"],
rows=[5432, 5432],
include_static_vectors=False,
),
MaxoutWindowEncoder(width=321, window_size=3, maxout_pieces=4, depth=2),
)
parser = build_tb_parser_model(
tok2vec=tok2vec,
state_type="parser",
extra_state_tokens=True,
hidden_width=65,
maxout_pieces=5,
use_upper=True,
)
return parser
def test_spancat_model_forward_backward(nO=5):
tok2vec = build_Tok2Vec_model(**get_tok2vec_kwargs())
docs = get_docs()
spans_list = []
lengths = []
for doc in docs:
spans_list.append(doc[:2])
spans_list.append(doc[1:4])
lengths.append(2)
spans = Ragged(
tok2vec.ops.asarray([[s.start, s.end] for s in spans_list], dtype="i"),
tok2vec.ops.asarray(lengths, dtype="i"),
)
model = build_spancat_model(tok2vec, reduce_mean(),
chain(Relu(nO=nO),
Logistic())).initialize(X=(docs, spans))
Y, backprop = model((docs, spans), is_train=True)
assert Y.shape == (spans.dataXd.shape[0], nO)
backprop(Y)
def test_tok2vec():
return build_Tok2Vec_model(**get_tok2vec_kwargs())
def test_spancat_model_init():
model = build_spancat_model(build_Tok2Vec_model(**get_tok2vec_kwargs()),
reduce_mean(), Logistic())
model.initialize()
