explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

revert commits that should have been on different, local branch

Browse Source
This commit is contained in:
svlandeg 2020-07-31 15:10:20 +02:00
parent d5d7fe5968
commit a52e1f99ff
4 changed files with 10 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@ -6,7 +6,7 @@ requires = [
"cymem>=2.0.2,<2.1.0", "cymem>=2.0.2,<2.1.0",
"preshed>=3.0.2,<3.1.0", "preshed>=3.0.2,<3.1.0",
"murmurhash>=0.28.0,<1.1.0", "murmurhash>=0.28.0,<1.1.0",
"thinc>=8.0.0a21,<8.0.0a30", "thinc>=8.0.0a19,<8.0.0a30",
"blis>=0.4.0,<0.5.0", "blis>=0.4.0,<0.5.0",
"pytokenizations", "pytokenizations",
"smart_open>=2.0.0,<3.0.0" "smart_open>=2.0.0,<3.0.0"

2
requirements.txt
View File

@ -1,7 +1,7 @@
# Our libraries # Our libraries
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
thinc>=8.0.0a21,<8.0.0a30 thinc>=8.0.0a19,<8.0.0a30
blis>=0.4.0,<0.5.0 blis>=0.4.0,<0.5.0
ml_datasets>=0.1.1 ml_datasets>=0.1.1
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0

4
setup.cfg
View File

@ -34,13 +34,13 @@ setup_requires =
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
thinc>=8.0.0a21,<8.0.0a30 thinc>=8.0.0a19,<8.0.0a30
install_requires = install_requires =
# Our libraries # Our libraries
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
thinc>=8.0.0a21,<8.0.0a30 thinc>=8.0.0a19,<8.0.0a30
blis>=0.4.0,<0.5.0 blis>=0.4.0,<0.5.0
wasabi>=0.7.1,<1.1.0 wasabi>=0.7.1,<1.1.0
srsly>=2.1.0,<3.0.0 srsly>=2.1.0,<3.0.0

14
spacy/cli/debug_model.py
View File

@ -2,7 +2,7 @@ from typing import Dict, Any, Optional
from pathlib import Path from pathlib import Path
from wasabi import msg from wasabi import msg
from thinc.api import require_gpu, fix_random_seed, set_dropout_rate, Adam, Config from thinc.api import require_gpu, fix_random_seed, set_dropout_rate, Adam, Config
from thinc.api import Model, DATA_VALIDATION from thinc.api import Model
import typer import typer
from ._util import Arg, Opt, debug_cli, show_validation_error, parse_config_overrides from ._util import Arg, Opt, debug_cli, show_validation_error, parse_config_overrides
@ -16,7 +16,7 @@ def debug_model_cli(
# fmt: off # fmt: off
ctx: typer.Context, # This is only used to read additional arguments ctx: typer.Context, # This is only used to read additional arguments
config_path: Path = Arg(..., help="Path to config file", exists=True), config_path: Path = Arg(..., help="Path to config file", exists=True),
pipe_name: str = Arg(..., help="Name of the pipe of which the model should be analysed"), section: str = Arg(..., help="Section that defines the model to be analysed"),
layers: str = Opt("", "--layers", "-l", help="Comma-separated names of layer IDs to print"), layers: str = Opt("", "--layers", "-l", help="Comma-separated names of layer IDs to print"),
dimensions: bool = Opt(False, "--dimensions", "-DIM", help="Show dimensions"), dimensions: bool = Opt(False, "--dimensions", "-DIM", help="Show dimensions"),
parameters: bool = Opt(False, "--parameters", "-PAR", help="Show parameters"), parameters: bool = Opt(False, "--parameters", "-PAR", help="Show parameters"),
@ -53,20 +53,20 @@ def debug_model_cli(
cfg = Config().from_disk(config_path) cfg = Config().from_disk(config_path)
with show_validation_error(): with show_validation_error():
try: try:
nlp, config = util.load_model_from_config(cfg, overrides=config_overrides) _, config = util.load_model_from_config(cfg, overrides=config_overrides)
except ValueError as e: except ValueError as e:
msg.fail(str(e), exits=1) msg.fail(str(e), exits=1)
seed = config.get("training", {}).get("seed", None) seed = config["pretraining"]["seed"]
if seed is not None: if seed is not None:
msg.info(f"Fixing random seed: {seed}") msg.info(f"Fixing random seed: {seed}")
fix_random_seed(seed) fix_random_seed(seed)
component = nlp.get_pipe(pipe_name) component = dot_to_object(config, section)
if hasattr(component, "model"): if hasattr(component, "model"):
model = component.model model = component.model
else: else:
msg.fail( msg.fail(
f"The component '{pipe_name}' does not specify an object that holds a Model.", f"The section '{section}' does not specify an object that holds a Model.",
exits=1, exits=1,
) )
debug_model(model, print_settings=print_settings) debug_model(model, print_settings=print_settings)
@ -90,9 +90,7 @@ def debug_model(model: Model, *, print_settings: Optional[Dict[str, Any]] = None
# STEP 1: Initializing the model and printing again # STEP 1: Initializing the model and printing again
Y = _get_output(model.ops.xp) Y = _get_output(model.ops.xp)
_set_output_dim(nO=Y.shape[-1], model=model) _set_output_dim(nO=Y.shape[-1], model=model)
DATA_VALIDATION.set(False) # The output vector might differ from the official type of the output layer
model.initialize(X=_get_docs(), Y=Y) model.initialize(X=_get_docs(), Y=Y)
DATA_VALIDATION.set(True)
if print_settings.get("print_after_init"): if print_settings.get("print_after_init"):
msg.info(f"After initialization:") msg.info(f"After initialization:")
_print_model(model, print_settings) _print_model(model, print_settings)