ExtractHandler

class lib.infer.handler.ExtractHandler(plugin: str, compile_model: bool = False, config_file: str | None = None)

Bases: ABC

Handles the execution of a plugin’s pre_process, process and post_process actions

Parameters:

plugin (str) – The name of the plugin that this handler is to use
compile_model (bool) – True to compile any PyTorch models
config_file (str | None) – Full path to a custom config file to load. None for default config

Attributes Summary

`batch_size`	The batch size of the plugin
`processors`	The processors which should have thread's launched for this handler
`runner`	The runner that runs this handler

Methods Summary

`__call__`([input_plugin, profile])	Build and start the plugin handler's runner
`init_model`()	Load the model, compile it, if requested, and send a warmup batch through.
`output_info`()	Called after the final item is put to the out queue.
`post_process`(batch)	Perform post-processing on the given batch object, ready for exit from the plugin.
`pre_process`(batch)	Override to perform plugin type specific behavior for pre-processing on the given batch object, ready for inference.
`process`(batch)	Override to plugin type specific processing to get results from the plugin's inference for the given batch.

Attributes Documentation

batch_size: The batch size of the plugin

processors: tuple[Literal['pre_process', 'process', 'post_process'], ...] = ('pre_process', 'process', 'post_process'): The processors which should have thread’s launched for this handler

runner: The runner that runs this handler

Methods Documentation

__call__(input_plugin: ExtractHandler | ExtractRunner | None = None, profile: bool = False) → ExtractRunner

Build and start the plugin handler’s runner

Parameters:

input_plugin (ExtractHandler | ExtractRunner | None) – The input plugin handler or it’s runner that feeds this handler. None if data is to be fed through the handler runner’s put method (ie, the first handler in an extraction chain). Default: None
profile (bool) – True if the runner is to be profiled, indicating that threads will not be started. Default: False

Return type:

The extract plugin handler’s runner for this handler

init_model() → None

Load the model, compile it, if requested, and send a warmup batch through. Called either from the main thread, if compiling, or from the inference thread if not.

Return type:: None

output_info() → None

Called after the final item is put to the out queue. Override for plugin runner specific output

Return type:: None

abstractmethod post_process(batch: ExtractBatch) → None

Perform post-processing on the given batch object, ready for exit from the plugin. Override for plugin type specific behavior

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for post-processing
Return type:: None

abstractmethod pre_process(batch: ExtractBatch) → None

Override to perform plugin type specific behavior for pre-processing on the given batch object, ready for inference.

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for pre-processing
Return type:: None

abstractmethod process(batch: ExtractBatch) → None

Override to plugin type specific processing to get results from the plugin’s inference for the given batch.

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for processing
Return type:: None

__call__(input_plugin: ExtractHandler | ExtractRunner | None = None, profile: bool = False) → ExtractRunner

Build and start the plugin handler’s runner

Parameters:

input_plugin (ExtractHandler | ExtractRunner | None) – The input plugin handler or it’s runner that feeds this handler. None if data is to be fed through the handler runner’s put method (ie, the first handler in an extraction chain). Default: None
profile (bool) – True if the runner is to be profiled, indicating that threads will not be started. Default: False

Return type:

The extract plugin handler’s runner for this handler

property batch_size: int: The batch size of the plugin

do_compile: True if any managed Torch modules are to be compiled

init_model() → None

Load the model, compile it, if requested, and send a warmup batch through. Called either from the main thread, if compiling, or from the inference thread if not.

Return type:: None

output_info() → None

Called after the final item is put to the out queue. Override for plugin runner specific output

Return type:: None

plugin: The extraction plugin that this handler manages

plugin_name: The name of the plugin that is being handled

plugin_type: Literal['detect', 'align', 'mask', 'identity', 'file']: The type of plugin that this handler manages

abstractmethod post_process(batch: ExtractBatch) → None

Perform post-processing on the given batch object, ready for exit from the plugin. Override for plugin type specific behavior

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for post-processing
Return type:: None

abstractmethod pre_process(batch: ExtractBatch) → None

Override to perform plugin type specific behavior for pre-processing on the given batch object, ready for inference.

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for pre-processing
Return type:: None

abstractmethod process(batch: ExtractBatch) → None

Override to plugin type specific processing to get results from the plugin’s inference for the given batch.

Parameters:: batch (ExtractBatch) – The incoming ExtractBatch to use for processing
Return type:: None

processors: tuple[Literal['pre_process', 'process', 'post_process'], ...] = ('pre_process', 'process', 'post_process'): The processors which should have thread’s launched for this handler

property runner: ExtractRunner: The runner that runs this handler