Function debug_model_cli

spacy/cli/debug_model.py:36–99

Analyze a Thinc model implementation. Includes checks for internal structure and activations during training. DOCS: https://spacy.io/api/cli#debug-model

(
    # 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
    ),
    component: str = Arg(
        ..., help="Name of the pipeline component of which the model should be analysed"
    ),
    layers: str = Opt(
        "", "--layers", "-l", help="Comma-separated names of layer IDs to print"
    ),
    dimensions: bool = Opt(False, "--dimensions", "-DIM", help="Show dimensions"),
    parameters: bool = Opt(False, "--parameters", "-PAR", help="Show parameters"),
    gradients: bool = Opt(False, "--gradients", "-GRAD", help="Show gradients"),
    attributes: bool = Opt(False, "--attributes", "-ATTR", help="Show attributes"),
    P0: bool = Opt(False, "--print-step0", "-P0", help="Print model before training"),
    P1: bool = Opt(
        False, "--print-step1", "-P1", help="Print model after initialization"
    ),
    P2: bool = Opt(False, "--print-step2", "-P2", help="Print model after training"),
    P3: bool = Opt(False, "--print-step3", "-P3", help="Print final predictions"),
    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
    # fmt: on
)

    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
)
def debug_model_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
    ),
    component: str = Arg(
        ..., help="Name of the pipeline component of which the model should be analysed"
    ),
    layers: str = Opt(
        "", "--layers", "-l", help="Comma-separated names of layer IDs to print"
    ),
    dimensions: bool = Opt(False, "--dimensions", "-DIM", help="Show dimensions"),
    parameters: bool = Opt(False, "--parameters", "-PAR", help="Show parameters"),
    gradients: bool = Opt(False, "--gradients", "-GRAD", help="Show gradients"),
    attributes: bool = Opt(False, "--attributes", "-ATTR", help="Show attributes"),
    P0: bool = Opt(False, "--print-step0", "-P0", help="Print model before training"),
    P1: bool = Opt(
        False, "--print-step1", "-P1", help="Print model after initialization"
    ),
    P2: bool = Opt(False, "--print-step2", "-P2", help="Print model after training"),
    P3: bool = Opt(False, "--print-step3", "-P3", help="Print final predictions"),
    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
    # fmt: on
):
    """
    Analyze a Thinc model implementation. Includes checks for internal structure
    and activations during training.

    DOCS: https://spacy.io/api/cli#debug-model
    """
    setup_gpu(use_gpu)
    layers = string_to_list(layers, intify=True)
    print_settings = {
        "dimensions": dimensions,
        "parameters": parameters,
        "gradients": gradients,
        "attributes": attributes,
        "layers": layers,
        "print_before_training": P0,
        "print_after_init": P1,
        "print_after_training": P2,
        "print_prediction": P3,
    }
    config_overrides = parse_config_overrides(ctx.args)
    with show_validation_error(config_path):
        raw_config = util.load_config(
            config_path, overrides=config_overrides, interpolate=False
        )
    config = raw_config.interpolate()
    allocator = config["training"]["gpu_allocator"]
    if use_gpu >= 0 and allocator:
        set_gpu_allocator(allocator)
    with show_validation_error(config_path):
        nlp = util.load_model_from_config(raw_config)
        config = nlp.config.interpolate()
        T = registry.resolve(config["training"], schema=ConfigSchemaTraining)  # type: ignore[arg-type]
    seed = T["seed"]