morpheus.stages.inference.inference_stage.InferenceStage
- class InferenceStage(c)[source]
Bases:
<a href="morpheus.pipeline.multi_message_stage.MultiMessageStage.html#morpheus.pipeline.multi_message_stage.MultiMessageStage">morpheus.pipeline.multi_message_stage.MultiMessageStage</a>
This class serves as the base for any inference stage. Inference stages operate differently than other stages due to the fact that they operate in a separate thread and have their own batch size which is separate from the pipeline batch size. Processing the inference work in a separate thread is necessary to support inference types that may require exclusive use of a single thread (i.e., TensorRT) without blocking the main thread.
Changing batch sizes for the inference stage requires breaking messages into smaller slices, running inference on the smaller slices, then recombining the inference output into the original batch size. This inference base class handles breaking and recombining batches and queing the inference work to be processed on another thread.
Inference stages that derive from this class need to implement the
<a href="#morpheus.stages.inference.inference_stage.InferenceStage._get_inference_worker">_get_inference_worker</a>
method which returns an implementation of the<a href="morpheus.stages.inference.inference_stage.InferenceWorker.html#morpheus.stages.inference.inference_stage.InferenceWorker">InferenceWorker</a>
class. Your<a href="morpheus.stages.inference.inference_stage.InferenceWorker.html#morpheus.stages.inference.inference_stage.InferenceWorker">InferenceWorker</a>
class must implement theprocess
andcalc_output_dims
methods. Theprocess
methods is where you provide implementation details on how to perform inference with theMultiInferenceMessage
batch. The worker uses thecalc_output_dims
to calculate the output dimensions of the pipeline batch that inference batch results are appended to.To add a C++ implementation for processing inference requests, you must implement the
_get_cpp_inference_node
method and implement<a href="#morpheus.stages.inference.inference_stage.InferenceStage.supports_cpp_node">supports_cpp_node</a>
in your worker to return True. Your pipeline can then use your C++ implementation by settinguse_cpp
to True in your pipeline configuration. See developer documentation for more details.- Parameters
- c
<a href="morpheus.config.Config.html#morpheus.config.Config">morpheus.config.Config</a>
Pipeline configuration instance.
- c
- Attributes
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.has_multi_input_ports">has_multi_input_ports</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.has_multi_output_ports">has_multi_output_ports</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.input_ports">input_ports</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.is_built">is_built</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.name">name</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.output_ports">output_ports</a>
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.unique_name">unique_name</a>
Indicates if this stage has multiple input ports.
Indicates if this stage has multiple output ports.
Input ports to this stage.
Indicates if this stage has been built.
The name of the stage.
Output ports from this stage.
Unique name of stage.
Methods
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.accepted_types">accepted_types</a>
()Accepted input types to this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.build">build</a>
(builder[, do_propagate])Build this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.can_build">can_build</a>
([check_ports])Determines if all inputs have been built allowing this node to be built.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.get_all_input_stages">get_all_input_stages</a>
()Get all input stages to this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.get_all_inputs">get_all_inputs</a>
()Get all input senders to this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.get_all_output_stages">get_all_output_stages</a>
()Get all output stages from this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.get_all_outputs">get_all_outputs</a>
()Get all output receivers from this stage.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.get_needed_columns">get_needed_columns</a>
()Stages which need to have columns inserted into the dataframe, should populate the
self._needed_columns
dictionary with mapping of column names to<a href="morpheus.common.html#morpheus.common.TypeId">morpheus.common.TypeId</a>
.<a href="#morpheus.stages.inference.inference_stage.InferenceStage.join">join</a>
()On all inference worker threads, this function applies join.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.on_start">on_start</a>
()This function can be overridden to add usecase-specific implementation at the start of any stage in the pipeline.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.start_async">start_async</a>
()This function is called along with on_start during stage initialization.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.stop">stop</a>
()Stops the inference workers and closes the inference queue.
<a href="#morpheus.stages.inference.inference_stage.InferenceStage.supports_cpp_node">supports_cpp_node</a>
()Specifies whether this Stage is capable of creating C++ nodes.
- _build(builder, in_ports_streams)[source]
This function is responsible for constructing this stage’s internal
mrc.SegmentObject
object. The input of this function contains the returned value from the upstream stage.The input values are the
mrc.Builder
for this stage and aStreamPair
tuple which contain the inputmrc.SegmentObject
object and the message data type.- Parameters
- builder
mrc.Builder
- in_ports_streams
morpheus.pipeline.pipeline.StreamPair
mrc.Builder
object for the pipeline. This should be used to construct/attach the internalmrc.SegmentObject
.List of tuples containing the input
mrc.SegmentObject
object and the message data type.- builder
- Returns
typing.List[morpheus.pipeline.pipeline.StreamPair]
List of tuples containing the output
mrc.SegmentObject
object from this stage and the message data type.
- abstract _get_inference_worker(inf_queue)[source]
Returns the main inference worker which manages requests possibly in another thread depending on which mode the pipeline is currently operating in.
- Parameters
- inf_queue
<a href="morpheus.utils.producer_consumer_queue.ProducerConsumerQueue.html#morpheus.utils.producer_consumer_queue.ProducerConsumerQueue">morpheus.utils.producer_consumer_queue.ProducerConsumerQueue</a>
Inference request queue.
- inf_queue
- Returns
<a href="morpheus.stages.inference.inference_stage.InferenceWorker.html#morpheus.stages.inference.inference_stage.InferenceWorker">InferenceWorker</a>
Inference worker implementation for stage.
- accepted_types()[source]
Accepted input types to this stage.
- Returns
- typing.Tuple
Tuple of input types.
- build(builder, do_propagate=True)[source]
Build this stage.
- Parameters
- builder
mrc.Builder
- do_propagatebool, optional
MRC segment for this stage.
Whether to propagate to build output stages, by default True.
- builder
- can_build(check_ports=False)[source]
Determines if all inputs have been built allowing this node to be built.
- Parameters
- check_portsbool, optional
Check if we can build based on the input ports, by default False.
- Returns
- bool
True if we can build, False otherwise.
- get_all_input_stages()[source]
Get all input stages to this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.StreamWrapper
]
All input stages.
- typing.List[
- get_all_inputs()[source]
Get all input senders to this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.Sender
]
All input senders.
- typing.List[
- get_all_output_stages()[source]
Get all output stages from this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.StreamWrapper
]
All output stages.
- typing.List[
- get_all_outputs()[source]
Get all output receivers from this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.Receiver
]
All output receivers.
- typing.List[
- get_needed_columns()[source]
Stages which need to have columns inserted into the dataframe, should populate the
self._needed_columns
dictionary with mapping of column names to<a href="morpheus.common.html#morpheus.common.TypeId">morpheus.common.TypeId</a>
. This will ensure that the columns are allocated and populated with null values.- property has_multi_input_ports: bool
Indicates if this stage has multiple input ports.
- Returns
- bool
True if stage has multiple input ports, False otherwise.
- property has_multi_output_ports: bool
Indicates if this stage has multiple output ports.
- Returns
- bool
True if stage has multiple output ports, False otherwise.
- property input_ports: List[morpheus.pipeline.receiver.Receiver]
Input ports to this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.Receiver
]
Input ports to this stage.
- typing.List[
- property is_built: bool
Indicates if this stage has been built.
- Returns
- bool
True if stage is built, False otherwise.
- async join()[source]
On all inference worker threads, this function applies join.
- property name: str
The name of the stage. Used in logging. Each derived class should override this property with a unique name.
- Returns
- str
Name of a stage.
- on_start()[source]
This function can be overridden to add usecase-specific implementation at the start of any stage in the pipeline.
- property output_ports: List[morpheus.pipeline.sender.Sender]
Output ports from this stage.
- Returns
- typing.List[
morpheus.pipeline.pipeline.Sender
]
Output ports from this stage.
- typing.List[
- async start_async()[source]
This function is called along with on_start during stage initialization. Allows stages to utilize the asyncio loop if needed.
- stop()[source]
Stops the inference workers and closes the inference queue.
- supports_cpp_node()[source]
Specifies whether this Stage is capable of creating C++ nodes. During the build phase, this value will be combined with
CppConfig.get_should_use_cpp()
to determine whether or not a C++ node is created. This is an instance method to allow runtime decisions and derived classes to override base implementations.- property unique_name: str
Unique name of stage. Generated by appending stage id to stage name.
- Returns
- str
Unique name of stage.