tft.apply_function_with_checkpoint

View source on GitHub

Applies a tensor-in-tensor-out function with variables to some Tensors.

tft.apply_function_with_checkpoint(
    fn, inputs, checkpoint, include=None, exclude=None
)

Variable values are loaded from the given checkpoint path. Note that the input_tensor_func, together with the checkpoint, will be converted to an all-constants graph, so ops requiring graph collections, such as table lookup (which requires a table init op being added to TABLE_INITIALIZERS collection), are not supported.

fn A tensor-in-tensor-out function that may contain variables.
inputs A list of Tensors to apply fn to.
checkpoint The checkpoint path to load variables from.
include An optional list/tuple of scope strings for filtering which variables from the VARIABLES collection to include. If None, all variables will be included.
exclude An optional list/tuple of scope strings for filtering which variables from the VARIABLES collection to exclude. If None, no variables will be excluded.

A Tensor or list of Tensors representing the application of fn.

ValueError if the input tensor-in-tensor-out function adds to TABLE_INITIALIZERS collections.