mirror of
https://github.com/explosion/spaCy.git
synced 2025-04-25 11:23:40 +03:00
Move rehearse functionality to existing train cli
This commit is contained in:
thomashacker
parent
97c86072e5
commit
e18a183f54
|
|
@ -1,83 +0,0 @@
|
|||
from typing import Optional, Dict, Any, Union
|
||||
from pathlib import Path
|
||||
from wasabi import msg
|
||||
import typer
|
||||
import logging
|
||||
import sys
|
||||
|
||||
from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
|
||||
from ._util import import_code, setup_gpu
|
||||
from ..training.loop import train as train_nlp
|
||||
from ..training.initialize import init_nlp
|
||||
from .. import util
|
||||
|
||||
|
||||
@app.command(
|
||||
"rehearse",
|
||||
context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
|
||||
)
|
||||
def rehearse_cli(
|
||||
# fmt: off
|
||||
ctx: typer.Context, # This is only used to read additional arguments
|
||||
config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
|
||||
output_path: Optional[Path] = Opt(None, "--output", "--output-path", "-o", help="Output directory to store trained pipeline in"),
|
||||
code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
|
||||
verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
|
||||
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
|
||||
# fmt: on
|
||||
):
|
||||
"""
|
||||
Rehearse a spaCy pipeline. Requires data in spaCy's binary format. To
|
||||
convert data from other formats, use the `spacy convert` command. The
|
||||
config file includes all settings and hyperparameters used during training.
|
||||
To override settings in the config, e.g. settings that point to local
|
||||
paths or that you want to experiment with, you can override them as
|
||||
command line options. For instance, --training.batch_size 128 overrides
|
||||
the value of "batch_size" in the block "[training]". The --code argument
|
||||
lets you pass in a Python file that's imported before training. It can be
|
||||
used to register custom functions and architectures that can then be
|
||||
referenced in the config.
|
||||
|
||||
DOCS: https://spacy.io/api/cli#rehearse
|
||||
"""
|
||||
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
|
||||
overrides = parse_config_overrides(ctx.args)
|
||||
import_code(code_path)
|
||||
rehearse(config_path, output_path, use_gpu=use_gpu, overrides=overrides)
|
||||
|
||||
|
||||
def rehearse(
|
||||
config_path: Union[str, Path],
|
||||
output_path: Optional[Union[str, Path]] = None,
|
||||
*,
|
||||
use_gpu: int = -1,
|
||||
overrides: Dict[str, Any] = util.SimpleFrozenDict(),
|
||||
):
|
||||
config_path = util.ensure_path(config_path)
|
||||
output_path = util.ensure_path(output_path)
|
||||
# Make sure all files and paths exists if they are needed
|
||||
if not config_path or (str(config_path) != "-" and not config_path.exists()):
|
||||
msg.fail("Config file not found", config_path, exits=1)
|
||||
if not output_path:
|
||||
msg.info("No output directory provided")
|
||||
else:
|
||||
if not output_path.exists():
|
||||
output_path.mkdir(parents=True)
|
||||
msg.good(f"Created output directory: {output_path}")
|
||||
msg.info(f"Saving to output directory: {output_path}")
|
||||
setup_gpu(use_gpu)
|
||||
with show_validation_error(config_path):
|
||||
config = util.load_config(config_path, overrides=overrides, interpolate=False)
|
||||
msg.divider("Initializing pipeline")
|
||||
with show_validation_error(config_path, hint_fill=False):
|
||||
nlp = init_nlp(config, use_gpu=use_gpu)
|
||||
msg.good("Initialized pipeline")
|
||||
msg.divider("Training pipeline")
|
||||
train_nlp(
|
||||
nlp,
|
||||
output_path,
|
||||
use_gpu=use_gpu,
|
||||
use_rehearse=True,
|
||||
stdout=sys.stdout,
|
||||
stderr=sys.stderr,
|
||||
)
|
||||
|
|
@ -22,7 +22,8 @@ def train_cli(
|
|||
output_path: Optional[Path] = Opt(None, "--output", "--output-path", "-o", help="Output directory to store trained pipeline in"),
|
||||
code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
|
||||
verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
|
||||
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
|
||||
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
|
||||
use_rehearse: bool = Opt(False, "--use_rehearse", "-r", help="Perform 'rehearsal updates' on a pre-trained model")
|
||||
# fmt: on
|
||||
):
|
||||
"""
|
||||
|
|
@ -42,7 +43,13 @@ def train_cli(
|
|||
util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
|
||||
overrides = parse_config_overrides(ctx.args)
|
||||
import_code(code_path)
|
||||
train(config_path, output_path, use_gpu=use_gpu, overrides=overrides)
|
||||
train(
|
||||
config_path,
|
||||
output_path,
|
||||
use_gpu=use_gpu,
|
||||
overrides=overrides,
|
||||
use_rehearse=use_rehearse,
|
||||
)
|
||||
|
||||
|
||||
def train(
|
||||
|
|
@ -51,6 +58,7 @@ def train(
|
|||
*,
|
||||
use_gpu: int = -1,
|
||||
overrides: Dict[str, Any] = util.SimpleFrozenDict(),
|
||||
use_rehearse: bool = False,
|
||||
):
|
||||
config_path = util.ensure_path(config_path)
|
||||
output_path = util.ensure_path(output_path)
|
||||
|
|
@ -72,4 +80,11 @@ def train(
|
|||
nlp = init_nlp(config, use_gpu=use_gpu)
|
||||
msg.good("Initialized pipeline")
|
||||
msg.divider("Training pipeline")
|
||||
train_nlp(nlp, output_path, use_gpu=use_gpu, stdout=sys.stdout, stderr=sys.stderr)
|
||||
train_nlp(
|
||||
nlp,
|
||||
output_path,
|
||||
use_gpu=use_gpu,
|
||||
stdout=sys.stdout,
|
||||
stderr=sys.stderr,
|
||||
use_rehearse=use_rehearse,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -1050,7 +1050,7 @@ in the section `[paths]`.
|
|||
> ```
|
||||
|
||||
```bash
|
||||
$ python -m spacy train [config_path] [--output] [--code] [--verbose] [--gpu-id] [overrides]
|
||||
$ python -m spacy train [config_path] [--output] [--code] [--verbose] [--gpu-id] [--use_rehearse] [overrides]
|
||||
```
|
||||
|
||||
| Name | Description |
|
||||
|
|
@ -1060,6 +1060,7 @@ $ python -m spacy train [config_path] [--output] [--code] [--verbose] [--gpu-id]
|
|||
| `--code`, `-c` | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
|
||||
| `--verbose`, `-V` | Show more detailed messages during training. ~~bool (flag)~~ |
|
||||
| `--gpu-id`, `-g` | GPU ID or `-1` for CPU. Defaults to `-1`. ~~int (option)~~ |
|
||||
| `--use_rehearse`, `-r` | Use 'rehearsal' updates on a pre-trained model to address the catastrophic forgetting problem. Defaults to `False`. ~~bool (flag)~~ |
|
||||
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
|
||||
| overrides | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~ |
|
||||
| **CREATES** | The final trained pipeline and the best trained pipeline. |
|
||||
|
|
@ -1135,38 +1136,6 @@ $ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [
|
|||
| overrides | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--training.dropout 0.2`. ~~Any (option/flag)~~ |
|
||||
| **CREATES** | The pretrained weights that can be used to initialize `spacy train`. |
|
||||
|
||||
## rehearse {id="rehearse",tag="command, experimental"}
|
||||
|
||||
This command is designed to fine-tune pre-trained models while also trying to address the “catastrophic forgetting” problem.
|
||||
It uses "rehearsal" updates that teach the current model to make predictions similar to an initial model. This feature is experimental.
|
||||
|
||||
<Infobox title="Please note" variant="warning">
|
||||
|
||||
The `rehearse` command outputs the sum of both losses from the `TrainablePipe.update` and `TrainablePipe.rehearse`.
|
||||
This can potentially cause the loss to increase drastically, even while the scores also increasing. It's likely due to the model making more different predictions than the intital model.
|
||||
|
||||
</Infobox>
|
||||
|
||||
> #### Example
|
||||
>
|
||||
> ```bash
|
||||
> $ python -m spacy rehearse config.cfg --output ./output --paths.train ./train --paths.dev ./dev
|
||||
> ```
|
||||
|
||||
```bash
|
||||
$ python -m spacy rehearse [config_path] [--output] [--code] [--verbose] [--gpu-id] [overrides]
|
||||
```
|
||||
|
||||
| Name | Description |
|
||||
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `config_path` | Path to [training config](/api/data-formats#config) file containing all settings and hyperparameters. If `-`, the data will be [read from stdin](/usage/training#config-stdin). ~~Union[Path, str] \(positional)~~ |
|
||||
| `--output`, `-o` | Directory to store trained pipeline in. Will be created if it doesn't exist. ~~Optional[Path] \(option)~~ |
|
||||
| `--code`, `-c` | Path to Python file with additional code to be imported. Allows [registering custom functions](/usage/training#custom-functions) for new architectures. ~~Optional[Path] \(option)~~ |
|
||||
| `--verbose`, `-V` | Show more detailed messages during training. ~~bool (flag)~~ |
|
||||
| `--gpu-id`, `-g` | GPU ID or `-1` for CPU. Defaults to `-1`. ~~int (option)~~ |
|
||||
| `--help`, `-h` | Show help message and available arguments. ~~bool (flag)~~ |
|
||||
| overrides | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~ |
|
||||
| **CREATES** | The final rehearse pipeline and the best rehearsed pipeline.
|
||||
|
||||
## evaluate {id="evaluate",version="2",tag="command"}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user