explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Try to debug segfault

Browse Source
This commit is contained in:
Matthew Honnibal 2024-12-10 19:27:16 +01:00
parent 18f23b5ad7
commit 1a4d21ccd5
1 changed files with 45 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

89
spacy/tests/training/test_pretraining.py
View File

@ -264,50 +264,51 @@ def test_pretraining_tagger():
pretrain(filled, tmp_dir)
def test_pretraining_training():
"""Test that training can use a pretrained Tok2Vec model"""
config = Config().from_str(pretrain_string_internal)
nlp = util.load_model_from_config(config, auto_fill=True, validate=False)
filled = nlp.config
pretrain_config = util.load_config(DEFAULT_CONFIG_PRETRAIN_PATH)
filled = pretrain_config.merge(filled)
train_config = util.load_config(DEFAULT_CONFIG_PATH)
filled = train_config.merge(filled)
with make_tempdir() as tmp_dir:
pretrain_dir = tmp_dir / "pretrain"
pretrain_dir.mkdir()
file_path = write_sample_jsonl(pretrain_dir)
filled["paths"]["raw_text"] = file_path
filled["pretraining"]["component"] = "tagger"
filled["pretraining"]["layer"] = "tok2vec"
train_dir = tmp_dir / "train"
train_dir.mkdir()
train_path, dev_path = write_sample_training(train_dir)
filled["paths"]["train"] = train_path
filled["paths"]["dev"] = dev_path
filled = filled.interpolate()
P = filled["pretraining"]
nlp_base = init_nlp(filled)
model_base = (
nlp_base.get_pipe(P["component"]).model.get_ref(P["layer"]).get_ref("embed")
)
embed_base = None
for node in model_base.walk():
if node.name == "hashembed":
embed_base = node
pretrain(filled, pretrain_dir)
pretrained_model = Path(pretrain_dir / "model3.bin")
assert pretrained_model.exists()
filled["initialize"]["init_tok2vec"] = str(pretrained_model)
nlp = init_nlp(filled)
model = nlp.get_pipe(P["component"]).model.get_ref(P["layer"]).get_ref("embed")
embed = None
for node in model.walk():
if node.name == "hashembed":
embed = node
# ensure that the tok2vec weights are actually changed by the pretraining
assert np.any(np.not_equal(embed.get_param("E"), embed_base.get_param("E")))
train(nlp, train_dir)
# Try to debug segfault on windows
#def test_pretraining_training():
# """Test that training can use a pretrained Tok2Vec model"""
# config = Config().from_str(pretrain_string_internal)
# nlp = util.load_model_from_config(config, auto_fill=True, validate=False)
# filled = nlp.config
# pretrain_config = util.load_config(DEFAULT_CONFIG_PRETRAIN_PATH)
# filled = pretrain_config.merge(filled)
# train_config = util.load_config(DEFAULT_CONFIG_PATH)
# filled = train_config.merge(filled)
# with make_tempdir() as tmp_dir:
# pretrain_dir = tmp_dir / "pretrain"
# pretrain_dir.mkdir()
# file_path = write_sample_jsonl(pretrain_dir)
# filled["paths"]["raw_text"] = file_path
# filled["pretraining"]["component"] = "tagger"
# filled["pretraining"]["layer"] = "tok2vec"
# train_dir = tmp_dir / "train"
# train_dir.mkdir()
# train_path, dev_path = write_sample_training(train_dir)
# filled["paths"]["train"] = train_path
# filled["paths"]["dev"] = dev_path
# filled = filled.interpolate()
# P = filled["pretraining"]
# nlp_base = init_nlp(filled)
# model_base = (
# nlp_base.get_pipe(P["component"]).model.get_ref(P["layer"]).get_ref("embed")
# )
# embed_base = None
# for node in model_base.walk():
# if node.name == "hashembed":
# embed_base = node
# pretrain(filled, pretrain_dir)
# pretrained_model = Path(pretrain_dir / "model3.bin")
# assert pretrained_model.exists()
# filled["initialize"]["init_tok2vec"] = str(pretrained_model)
# nlp = init_nlp(filled)
# model = nlp.get_pipe(P["component"]).model.get_ref(P["layer"]).get_ref("embed")
# embed = None
# for node in model.walk():
# if node.name == "hashembed":
# embed = node
# # ensure that the tok2vec weights are actually changed by the pretraining
# assert np.any(np.not_equal(embed.get_param("E"), embed_base.get_param("E")))
# train(nlp, train_dir)
def write_sample_jsonl(tmp_dir):