transform_dl_sample_batchTransformDlSampleBatchTransformDlSampleBatchtransform_dl_sample_batchT_transform_dl_sample_batch

HALCON ScriptCpp++.NETPythonC

Short description

transform_dl_sample_batchTransformDlSampleBatchTransformDlSampleBatchtransform_dl_sample_batchT_transform_dl_sample_batch — Apply a pipeline of transforms on a set of images.

Signature

transform_dl_sample_batch( dl_transform_pipeline TransformPipeline, dict DLSampleBatch, out dict DLResultBatch )void TransformDlSampleBatch( const HTuple& TransformPipeline, const HTuple& DLSampleBatch, HTuple* DLResultBatch )static void HOperatorSet.TransformDlSampleBatch( HTuple transformPipeline, HTuple DLSampleBatch, out HTuple DLResultBatch )def transform_dl_sample_batch( transform_pipeline: HHandle, dlsample_batch: Sequence[HHandle] ) -> Sequence[HHandle]

Herror T_transform_dl_sample_batch( const Htuple TransformPipeline, const Htuple DLSampleBatch, Htuple* DLResultBatch )

HDictArray HDlTransformPipeline::TransformDlSampleBatch( const HDictArray& DLSampleBatch ) const

HDict[] HDlTransformPipeline.TransformDlSampleBatch( HDict[] DLSampleBatch )

Description

transform_dl_sample_batchTransformDlSampleBatch transforms a batch of samples prior to their use in train_dl_model_batchTrainDlModelBatch and apply_dl_modelApplyDlModel. The transformations defined in TransformPipelinetransformPipelinetransform_pipeline may include adapting the image dimensions, scaling the gray value range, and applying data augmentation methods.

Besides the image data keys image and image_id contained in DLSampleBatchDLSampleBatchdlsample_batch, annotations are also transformed if present. Currently, only keys for object detection models (including instance segmentation) are supported. The behavior for 'instance_type'"instance_type" = 'rectangle2'"rectangle2" can be influenced by the parameters 'ignore_direction'"ignore_direction" and 'class_ids_no_orientation'"class_ids_no_orientation", see get_dl_transform_pipeline_paramGetDlTransformPipelineParam. If DLSampleBatchDLSampleBatchdlsample_batch contains annotation keys for other model types, an error may be raised.

In addition to transformed keys, DLResultBatchDLResultBatchdlresult_batch contains

• 'transformed_full_domain'"transformed_full_domain": Transformation of the rectangular full domain of the input image, clipped to output.

• 'back_transform'"back_transform": Transformation that can be used together with projective_trans_pixelProjectiveTransPixel or projective_trans_regionProjectiveTransRegion to transform inference results of apply_dl_modelApplyDlModel back to the coordinate system of the original image.

Execution information

Execution information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).

• Multithreading scope: global (may be called from any thread).

• Automatically parallelized on internal data level.

Parameters

TransformPipelinetransformPipelinetransform_pipeline (input_control) dl_transform_pipeline → (handle)HTuple (HHandle)HDlTransformPipeline, HTuple (IntPtr)HHandleHtuple (handle)

Transform pipeline handle.

DLSampleBatchDLSampleBatchdlsample_batch (input_control) dict-array → (handle)HTuple (HHandle)HDict, HTuple (IntPtr)Sequence[HHandle]Htuple (handle)

Input data.

DLResultBatchDLResultBatchdlresult_batch (output_control) dict-array → (handle)HTuple (HHandle)HDict, HTuple (IntPtr)Sequence[HHandle]Htuple (handle)

Result data.

Combinations with other operators

Combinations

Possible predecessors

create_dl_transform_pipelineCreateDlTransformPipeline

Possible successors

train_dl_model_batchTrainDlModelBatch, apply_dl_modelApplyDlModel

See also

get_dl_transform_pipeline_paramGetDlTransformPipelineParam, set_dl_transform_pipeline_paramSetDlTransformPipelineParam

Module

Foundation