polygraphy.backend.base.runner.BaseRunner Class Reference

Inheritance diagram for polygraphy.backend.base.runner.BaseRunner:

Collaboration diagram for polygraphy.backend.base.runner.BaseRunner:

Public Member Functions
def	__init__ (self, name=None, prefix=None)
def	last_inference_time (self)
def	__enter__ (self)
def	__exit__ (self, exc_type, exc_value, traceback)
def	activate_impl (self)
def	activate (self)
def	infer_impl (self)
def	infer (self, feed_dict)
def	get_input_metadata (self)
def	deactivate_impl (self)
def	deactivate (self)
def	__del__ (self)

Public Attributes
	name
	inference_time
	is_active

Static Public Attributes
	RUNNER_COUNTS = defaultdict(int)

Detailed Description

The base class for runner objects. All runners should override the functions and attributes specified here.

Constructor & Destructor Documentation

__init__()

def polygraphy.backend.base.runner.BaseRunner.__init__	(		self,
			name = None,
			prefix = None
	)

Args:
    name (str):
    The name to use for this runner.
    prefix (str):
    The human-readable name prefix to use for this runner.
    A runner count and timestamp will be appended to this prefix.
    Only used if name is not provided.

Reimplemented in polygraphy.backend.onnxrt.runner.OnnxrtRunner, polygraphy.backend.onnx.runner.OnnxTfRunner, polygraphy.backend.cntk.runner.CNTKRunner, and polygraphy.backend.trt.runner.TrtRunner.

__del__()

def polygraphy.backend.base.runner.BaseRunner.__del__

(

self

)

Member Function Documentation

last_inference_time()

def polygraphy.backend.base.runner.BaseRunner.last_inference_time

(

self

)

Returns the total inference time required during the last call to ``infer()``.

Returns:
    float: The time in seconds, or None if runtime was not measured by the runner.

__enter__()

def polygraphy.backend.base.runner.BaseRunner.__enter__

(

self

)

Here is the call graph for this function:

__exit__()

def polygraphy.backend.base.runner.BaseRunner.__exit__	(		self,
			exc_type,
			exc_value,
			traceback
	)

Here is the call graph for this function:

activate_impl()

def polygraphy.backend.base.runner.BaseRunner.activate_impl

(

self

)

Implementation for runner activation. Derived classes should override this function
rather than ``activate()``.

Reimplemented in polygraphy.backend.trt_legacy.TrtLegacyRunner, polygraphy.backend.tf.runner.TfRunner, polygraphy.backend.trt.runner.TrtRunner, polygraphy.backend.pyt.runner.PytRunner, polygraphy.backend.onnxrt.runner.OnnxrtRunner, polygraphy.backend.onnx.runner.OnnxTfRunner, and polygraphy.backend.cntk.runner.CNTKRunner.

activate()

def polygraphy.backend.base.runner.BaseRunner.activate

(

self

)

Activate the runner for inference. This may involve allocating GPU buffers, for example.

Here is the caller graph for this function:

infer_impl()

def polygraphy.backend.base.runner.BaseRunner.infer_impl

(

self

)

Implementation for runner inference. Derived classes should override this function
rather than ``infer()``

Here is the caller graph for this function:

infer()

def polygraphy.backend.base.runner.BaseRunner.infer	(		self,
			feed_dict
	)

Runs inference using the provided feed_dict.

Args:
    feed_dict (OrderedDict[str, numpy.ndarray]): A mapping of input tensor names to corresponding input NumPy arrays.

Returns:
    OrderedDict[str, numpy.ndarray]:
    A mapping of output tensor names to their corresponding NumPy arrays.
    IMPORTANT: Runners may reuse these output buffers. Thus, if you need to save
    outputs from multiple inferences, you should make a copy with ``copy.copy(outputs)``.

Here is the call graph for this function:

get_input_metadata()

def polygraphy.backend.base.runner.BaseRunner.get_input_metadata

(

self

)

Returns information about the inputs of the model.
Shapes here may include dynamic dimensions, represented by ``None``.
Must be called only after activate() and before deactivate().

Returns:
    TensorMetadata: Input names, shapes, and data types.

Reimplemented in polygraphy.backend.trt_legacy.TrtLegacyRunner, polygraphy.backend.tf.runner.TfRunner, polygraphy.backend.onnx.runner.OnnxTfRunner, polygraphy.backend.pyt.runner.PytRunner, polygraphy.backend.onnxrt.runner.OnnxrtRunner, and polygraphy.backend.trt.runner.TrtRunner.

Here is the caller graph for this function:

deactivate_impl()

def polygraphy.backend.base.runner.BaseRunner.deactivate_impl

(

self

)

Implementation for runner deactivation. Derived classes should override this function
rather than ``deactivate()``.

Reimplemented in polygraphy.backend.trt_legacy.TrtLegacyRunner, polygraphy.backend.trt.runner.TrtRunner, polygraphy.backend.tf.runner.TfRunner, polygraphy.backend.onnx.runner.OnnxTfRunner, and polygraphy.backend.onnxrt.runner.OnnxrtRunner.

deactivate()

def polygraphy.backend.base.runner.BaseRunner.deactivate

(

self

)

Deactivate the runner.

Here is the caller graph for this function:

Member Data Documentation

RUNNER_COUNTS

polygraphy.backend.base.runner.BaseRunner.RUNNER_COUNTS = defaultdict(int)

static

name

polygraphy.backend.base.runner.BaseRunner.name

inference_time

polygraphy.backend.base.runner.BaseRunner.inference_time

is_active

polygraphy.backend.base.runner.BaseRunner.is_active

---

The documentation for this class was generated from the following file:

• backend/base/runner.py