![]() |
Interprets a program in this instruction language and returns the result.
Aliases:
tfp.experimental.auto_batching.frontend.instructions.interpret
tfp.experimental.auto_batching.frontend.st.inst.interpret
tfp.experimental.auto_batching.frontend.stack.inst.interpret
tfp.experimental.auto_batching.stack_optimization.inst.interpret
tfp.experimental.auto_batching.stackless.inst.interpret
tfp.experimental.auto_batching.instructions.interpret(
program,
*inputs
)
This is a definitional interpreter; its purpose is to define the semantics of the instruction language. As such, it does no auto-batching, and generally strives to be as simple as possible. It also does not stage graph computations, so will only work in Eager mode TensorFlow.
Args:
program
: The Program tuple to interpret.*inputs
: Values to pass to the program. The length ofinputs
must be the same as the length ofprogram.vars_in
.
Returns:
results
: A tuple of results, which are the values of the variables listed inprogram.out_vars
at termination.
Raises:
ValueError
: If an internal invariant is violated, or an error is detected in the program being interpreted.