Function to_static

python/paddle/distributed/auto_parallel/api.py:3654–3832

Converts the ``layer`` with distributed tensor (constructed from ``paddle.distributed.shard_tensor``) to a static graph. ``to_static`` returns a DistModel instance containing the static graph for distributed training, evaluation and prediction. Args: layer(paddle.nn.Lay

(
    layer: Layer,
    loader: ShardDataloader | DataLoader | None = None,
    loss: Layer | Callable[..., Any] | None = None,
    optimizer: Optimizer | None = None,
    strategy: Strategy | None = None,
    input_spec: list[list[DistributedInputSpec]] | None = None,
)

def to_static(
    layer: Layer,
    loader: ShardDataloader | DataLoader | None = None,
    loss: Layer | Callable[..., Any] | None = None,
    optimizer: Optimizer | None = None,
    strategy: Strategy | None = None,
    input_spec: list[list[DistributedInputSpec]] | None = None,
) -> DistModel:
    """
    Converts the ``layer`` with distributed tensor (constructed from
    ``paddle.distributed.shard_tensor``) to a static graph. ``to_static``
    returns a DistModel instance containing the static graph for
    distributed training, evaluation and prediction.

    Args:
        layer(paddle.nn.Layer): The layer in dygraph mode, the parameters
            or its inputs can be distributed tensors.
        loader(ShardDataloader|paddle.io.DataLoader): The data loader used in dygraph mode,
            used to infer inputs_spec and labels_spec.
        loss(Loss|Callable|None, optional): The loss function for training
            or evaluating the model. Can be a `paddle.nn.Layer` instance or
            any callable function. Default: None.
        optimizer(paddle.optimizer.Optimizer|_ShardOptimizer|None, optional):
            The optimizer for training. It can `paddle.optimizer.Optimizer`
            or `_ShardOptimizer` wrapped by `shard_optimizer`. Default: None.
        strategy(paddle.distributed.Strategy|None, optional): Configs for
            parallel strategies and optimization settings (e.g. sharding,
            pipeline parallelism). Default: None.
        input_spec(list[list[paddle.distributed.DistributedInputSpec]]|None, optional):
            The custom input specs specify the shape, dtype, and name information
            of model inputs and labels. If it is not None, the input specs and
            label specs will be inferred from the custom input specs. The custom
            input specs should be a list containing two sublists: the first
            sublist represents theinput specs, and the second sublist represents
            the label specs. Default: None.

    Returns:
        DistModel: A ``DistModel`` instance converted the input ``layer``.

    Examples:
        .. code-block:: pycon

            >>> import numpy as np
            >>> import paddle
            >>> import paddle.distributed as dist
            >>> from paddle import nn
            >>> from paddle.distributed import Replicate, Shard

            >>> BATCH_SIZE = 4
            >>> BATCH_NUM = 4
            >>> IMAGE_SIZE = 16
            >>> CLASS_NUM = 8
            >>> class RandomDataset(paddle.io.Dataset):  # type: ignore[type-arg]
            ...     def __init__(self, images, labels, num_samples):
            ...         self.images = images
            ...         self.labels = labels
            ...         self.num_samples = num_samples
            ...