mirror of
https://github.com/explosion/spaCy.git
synced 2025-04-21 17:41:59 +03:00
Add flag to skip saving model-last
This commit is contained in:
Adriane Boyd
parent
a562767336
commit
6d38cc10ff
|
|
@ -23,6 +23,7 @@ def pretrain_cli(
|
|||
resume_path: Optional[Path] = Opt(None, "--resume-path", "-r", help="Path to pretrained weights from which to resume pretraining"),
|
||||
epoch_resume: Optional[int] = Opt(None, "--epoch-resume", "-er", help="The epoch to resume counting from when using --resume-path. Prevents unintended overwriting of existing weight files."),
|
||||
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
|
||||
skip_last: bool = Opt(False, "--skip-last", "-L", help="Skip saving model-last.bin"),
|
||||
# fmt: on
|
||||
):
|
||||
"""
|
||||
|
|
@ -74,6 +75,7 @@ def pretrain_cli(
|
|||
epoch_resume=epoch_resume,
|
||||
use_gpu=use_gpu,
|
||||
silent=False,
|
||||
skip_last=skip_last,
|
||||
)
|
||||
msg.good("Successfully finished pretrain")
|
||||
|
||||
|
|
|
|||
|
|
@ -165,7 +165,8 @@ def test_pretraining_default():
|
|||
|
||||
|
||||
@pytest.mark.parametrize("objective", CHAR_OBJECTIVES)
|
||||
def test_pretraining_tok2vec_characters(objective):
|
||||
@pytest.mark.parametrize("skip_last", (True, False))
|
||||
def test_pretraining_tok2vec_characters(objective, skip_last):
|
||||
"""Test that pretraining works with the character objective"""
|
||||
config = Config().from_str(pretrain_string_listener)
|
||||
config["pretraining"]["objective"] = objective
|
||||
|
|
@ -178,11 +179,14 @@ def test_pretraining_tok2vec_characters(objective):
|
|||
filled["paths"]["raw_text"] = file_path
|
||||
filled = filled.interpolate()
|
||||
assert filled["pretraining"]["component"] == "tok2vec"
|
||||
pretrain(filled, tmp_dir)
|
||||
pretrain(filled, tmp_dir, skip_last=skip_last)
|
||||
assert Path(tmp_dir / "model0.bin").exists()
|
||||
assert Path(tmp_dir / "model4.bin").exists()
|
||||
assert Path(tmp_dir / "model-last.bin").exists()
|
||||
assert not Path(tmp_dir / "model5.bin").exists()
|
||||
if skip_last:
|
||||
assert not Path(tmp_dir / "model-last.bin").exists()
|
||||
else:
|
||||
assert Path(tmp_dir / "model-last.bin").exists()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("objective", VECTOR_OBJECTIVES)
|
||||
|
|
|
|||
|
|
@ -24,6 +24,7 @@ def pretrain(
|
|||
epoch_resume: Optional[int] = None,
|
||||
use_gpu: int = -1,
|
||||
silent: bool = True,
|
||||
skip_last: bool = False,
|
||||
):
|
||||
msg = Printer(no_print=silent)
|
||||
if config["training"]["seed"] is not None:
|
||||
|
|
@ -98,7 +99,8 @@ def pretrain(
|
|||
_save_model(epoch)
|
||||
tracker.epoch_loss = 0.0
|
||||
finally:
|
||||
_save_model(P["max_epochs"], is_last=True)
|
||||
if not skip_last:
|
||||
_save_model(P["max_epochs"], is_last=True)
|
||||
|
||||
|
||||
def ensure_docs(examples_or_docs: Iterable[Union[Doc, Example]]) -> List[Doc]:
|
||||
|
|
|
|||
|
|
@ -1122,17 +1122,18 @@ auto-generated by setting `--pretraining` on
|
|||
$ python -m spacy pretrain [config_path] [output_dir] [--code] [--resume-path] [--epoch-resume] [--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_dir` | Directory to save binary weights to on each epoch. ~~Path (positional)~~ |
|
||||
| `--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)~~ |
|
||||
| `--resume-path`, `-r` | Path to pretrained weights from which to resume pretraining. ~~Optional[Path] \(option)~~ |
|
||||
| `--epoch-resume`, `-er` | The epoch to resume counting from when using `--resume-path`. Prevents unintended overwriting of existing weight files. ~~Optional[int] \(option)~~ |
|
||||
| `--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. `--training.dropout 0.2`. ~~Any (option/flag)~~ |
|
||||
| **CREATES** | The pretrained weights that can be used to initialize `spacy train`. |
|
||||
| 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_dir` | Directory to save binary weights to on each epoch. ~~Path (positional)~~ |
|
||||
| `--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)~~ |
|
||||
| `--resume-path`, `-r` | Path to pretrained weights from which to resume pretraining. ~~Optional[Path] \(option)~~ |
|
||||
| `--epoch-resume`, `-er` | The epoch to resume counting from when using `--resume-path`. Prevents unintended overwriting of existing weight files. ~~Optional[int] \(option)~~ |
|
||||
| `--gpu-id`, `-g` | GPU ID or `-1` for CPU. Defaults to `-1`. ~~int (option)~~ |
|
||||
| `--skip-last`, `-L` <Tag variant="new">3.5.2</Tag> | Skip saving `model-last.bin`. 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. `--training.dropout 0.2`. ~~Any (option/flag)~~ |
|
||||
| **CREATES** | The pretrained weights that can be used to initialize `spacy train`. |
|
||||
|
||||
## evaluate {id="evaluate",version="2",tag="command"}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user