Face Recognition(人脸识别)#

fastdeploy.vision.faceid.AdaFace#

class fastdeploy.vision.faceid.AdaFace(model_file, params_file='', runtime_option=None, model_format=<ModelFormat.ONNX: 2>)[source]#

Load a AdaFace model exported by PaddleClas.

Parameters

  • model_file – (str)Path of model file, e.g adaface/model.pdmodel

  • params_file – (str)Path of parameters file, e.g adaface/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string

  • runtime_option – (fastdeploy.RuntimeOption)RuntimeOption for inference this model, if it’s None, will use the default backend on CPU

  • model_format – (fastdeploy.ModelForamt)Model format of the loaded model

batch_predict(images)[source]#

Detect a batch of input image list

Parameters

im – (list of numpy.ndarray) The input image list, each element is a 3-D array with layout HWC, BGR format

:return list of DetectionResult

get_profile_time()#

Get profile time of Runtime after the profile process is done.

property postprocessor#

Get AdaFacePostprocessor object of the loaded model

:return AdaFacePostprocessor

predict(im)[source]#

Detect an input image

Parameters

im – (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format

Returns

DetectionResult

property preprocessor#

Get AdaFacePreprocessor object of the loaded model

:return AdaFacePreprocessor

fastdeploy.vision.faceid.CosFace#

class fastdeploy.vision.faceid.CosFace(model_file, params_file='', runtime_option=None, model_format=<ModelFormat.ONNX: 2>)[source]#

Load a CosFace model exported by PaddleClas. :param model_file: (str)Path of model file, e.g CosFace/model.pdmodel :param params_file: (str)Path of parameters file, e.g CosFace/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string :param runtime_option: (fastdeploy.RuntimeOption)RuntimeOption for inference this model, if it’s None, will use the default backend on CPU :param model_format: (fastdeploy.ModelForamt)Model format of the loaded model

batch_predict(images)#

Detect a batch of input image list

Parameters

im – (list of numpy.ndarray) The input image list, each element is a 3-D array with layout HWC, BGR format

:return list of DetectionResult

get_profile_time()#

Get profile time of Runtime after the profile process is done.

property postprocessor#

Get InsightFaceRecognitionPostprocessor object of the loaded model

:return InsightFaceRecognitionPostprocessor

predict(im)#

Detect an input image

Parameters

im – (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format

Returns

DetectionResult

property preprocessor#

Get InsightFaceRecognitionPreprocessor object of the loaded model

:return InsightFaceRecognitionPreprocessor

fastdeploy.vision.faceid.ArcFace#

class fastdeploy.vision.faceid.ArcFace(model_file, params_file='', runtime_option=None, model_format=<ModelFormat.ONNX: 2>)[source]#

Load a ArcFace model exported by PaddleClas. :param model_file: (str)Path of model file, e.g ArcFace/model.pdmodel :param params_file: (str)Path of parameters file, e.g ArcFace/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string :param runtime_option: (fastdeploy.RuntimeOption)RuntimeOption for inference this model, if it’s None, will use the default backend on CPU :param model_format: (fastdeploy.ModelForamt)Model format of the loaded model

batch_predict(images)#

Detect a batch of input image list

Parameters

im – (list of numpy.ndarray) The input image list, each element is a 3-D array with layout HWC, BGR format

:return list of DetectionResult

get_profile_time()#

Get profile time of Runtime after the profile process is done.

property postprocessor#

Get InsightFaceRecognitionPostprocessor object of the loaded model

:return InsightFaceRecognitionPostprocessor

predict(im)#

Detect an input image

Parameters

im – (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format

Returns

DetectionResult

property preprocessor#

Get InsightFaceRecognitionPreprocessor object of the loaded model

:return InsightFaceRecognitionPreprocessor

fastdeploy.vision.faceid.PartialFC#

class fastdeploy.vision.faceid.PartialFC(model_file, params_file='', runtime_option=None, model_format=<ModelFormat.ONNX: 2>)[source]#

Load a PartialFC model exported by PaddleClas. :param model_file: (str)Path of model file, e.g PartialFC/model.pdmodel :param params_file: (str)Path of parameters file, e.g PartialFC/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string :param runtime_option: (fastdeploy.RuntimeOption)RuntimeOption for inference this model, if it’s None, will use the default backend on CPU :param model_format: (fastdeploy.ModelForamt)Model format of the loaded model

batch_predict(images)#

Detect a batch of input image list

Parameters

im – (list of numpy.ndarray) The input image list, each element is a 3-D array with layout HWC, BGR format

:return list of DetectionResult

get_profile_time()#

Get profile time of Runtime after the profile process is done.

property postprocessor#

Get InsightFaceRecognitionPostprocessor object of the loaded model

:return InsightFaceRecognitionPostprocessor

predict(im)#

Detect an input image

Parameters

im – (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format

Returns

DetectionResult

property preprocessor#

Get InsightFaceRecognitionPreprocessor object of the loaded model

:return InsightFaceRecognitionPreprocessor

fastdeploy.vision.faceid.VPL#

class fastdeploy.vision.faceid.VPL(model_file, params_file='', runtime_option=None, model_format=<ModelFormat.ONNX: 2>)[source]#

Load a VPL model exported by PaddleClas. :param model_file: (str)Path of model file, e.g VPL/model.pdmodel :param params_file: (str)Path of parameters file, e.g VPL/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string :param runtime_option: (fastdeploy.RuntimeOption)RuntimeOption for inference this model, if it’s None, will use the default backend on CPU :param model_format: (fastdeploy.ModelForamt)Model format of the loaded model

batch_predict(images)#

Detect a batch of input image list

Parameters

im – (list of numpy.ndarray) The input image list, each element is a 3-D array with layout HWC, BGR format

:return list of DetectionResult

get_profile_time()#

Get profile time of Runtime after the profile process is done.

property postprocessor#

Get InsightFaceRecognitionPostprocessor object of the loaded model

:return InsightFaceRecognitionPostprocessor

predict(im)#

Detect an input image

Parameters

im – (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format

Returns

DetectionResult

property preprocessor#

Get InsightFaceRecognitionPreprocessor object of the loaded model

:return InsightFaceRecognitionPreprocessor