mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
333b1a308b
* Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
90 lines
2.5 KiB
Python
90 lines
2.5 KiB
Python
import pytest
|
|
import os
|
|
import ctypes
|
|
from pathlib import Path
|
|
from spacy import util
|
|
from spacy import prefer_gpu, require_gpu
|
|
from spacy.ml._precomputable_affine import PrecomputableAffine, _backprop_precomputable_affine_padding
|
|
|
|
|
|
@pytest.fixture
|
|
def is_admin():
|
|
"""Determine if the tests are run as admin or not."""
|
|
try:
|
|
admin = os.getuid() == 0
|
|
except AttributeError:
|
|
admin = ctypes.windll.shell32.IsUserAnAdmin() != 0
|
|
|
|
return admin
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["hello/world", "hello world"])
|
|
def test_util_ensure_path_succeeds(text):
|
|
path = util.ensure_path(text)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
@pytest.mark.parametrize("package", ["numpy"])
|
|
def test_util_is_package(package):
|
|
"""Test that an installed package via pip is recognised by util.is_package."""
|
|
assert util.is_package(package)
|
|
|
|
|
|
@pytest.mark.parametrize("package", ["thinc"])
|
|
def test_util_get_package_path(package):
|
|
"""Test that a Path object is returned for a package name."""
|
|
path = util.get_package_path(package)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
|
|
model = PrecomputableAffine(nO=nO, nI=nI, nF=nF, nP=nP).initialize()
|
|
assert model.get_param("W").shape == (nF, nO, nP, nI)
|
|
tensor = model.ops.alloc((10, nI))
|
|
Y, get_dX = model.begin_update(tensor)
|
|
assert Y.shape == (tensor.shape[0] + 1, nF, nO, nP)
|
|
dY = model.ops.alloc((15, nO, nP))
|
|
ids = model.ops.alloc((15, nF))
|
|
ids[1, 2] = -1
|
|
dY[1] = 1
|
|
assert not model.has_grad("pad")
|
|
d_pad = _backprop_precomputable_affine_padding(model, dY, ids)
|
|
assert d_pad[0, 2, 0, 0] == 1.0
|
|
ids.fill(0.0)
|
|
dY.fill(0.0)
|
|
dY[0] = 0
|
|
ids[1, 2] = 0
|
|
ids[1, 1] = -1
|
|
ids[1, 0] = -1
|
|
dY[1] = 1
|
|
ids[2, 0] = -1
|
|
dY[2] = 5
|
|
d_pad = _backprop_precomputable_affine_padding(model, dY, ids)
|
|
assert d_pad[0, 0, 0, 0] == 6
|
|
assert d_pad[0, 1, 0, 0] == 1
|
|
assert d_pad[0, 2, 0, 0] == 0
|
|
|
|
|
|
def test_prefer_gpu():
|
|
try:
|
|
import cupy # noqa: F401
|
|
except ImportError:
|
|
assert not prefer_gpu()
|
|
|
|
|
|
def test_require_gpu():
|
|
try:
|
|
import cupy # noqa: F401
|
|
except ImportError:
|
|
with pytest.raises(ValueError):
|
|
require_gpu()
|
|
|
|
|
|
def test_ascii_filenames():
|
|
"""Test that all filenames in the project are ASCII.
|
|
See: https://twitter.com/_inesmontani/status/1177941471632211968
|
|
"""
|
|
root = Path(__file__).parent.parent
|
|
for path in root.glob("**/*"):
|
|
assert all(ord(c) < 128 for c in path.name), path.name
|