Matting(图像抠图)#

fastdeploy.vision.matting.MODNet#

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

Load a MODNet model exported by MODNet.

Parameters

  • model_file – (str)Path of model file, e.g ./modnet.onnx

  • params_file – (str)Path of parameters file, e.g yolox/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

property alpha#

Argument for image preprocessing step, alpha value for normalization, default alpha = {1.f / 127.5f, 1.f / 127.5f, 1.f / 127.5f}

property beta#

Argument for image preprocessing step, beta value for normalization, default beta = {-1.f, -1.f, -1.f}

get_profile_time()#

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

predict(input_image)[source]#

Predict the matting result for an input image

Parameters

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

Returns

MattingResult

property size#

Argument for image preprocessing step, the preprocess image size, tuple of (width, height), default size = [256,256]

property swap_rb#

Argument for image preprocessing step, whether to swap the B and R channel, such as BGR->RGB, default True.

fastdeploy.vision.matting.PPMatting#

class fastdeploy.vision.matting.PPMatting(model_file, params_file, config_file, runtime_option=None, model_format=<ModelFormat.PADDLE: 1>)[source]#

Load a PPMatting model exported by PaddleSeg.

Parameters

  • model_file – (str)Path of model file, e.g PPMatting-512/model.pdmodel

  • params_file – (str)Path of parameters file, e.g PPMatting-512/model.pdiparams, if the model_fomat is ModelFormat.ONNX, this param will be ignored, can be set as empty string

  • config_file – (str)Path of configuration file for deployment, e.g PPMatting-512/deploy.yml

  • 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

get_profile_time()#

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

predict(input_image)[source]#

Predict the matting result for an input image

Parameters

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

Returns

MattingResult

fastdeploy.vision.matting.RobustVideoMatting#

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

Load a video matting model exported by RobustVideoMatting.

Parameters

  • model_file – (str)Path of model file, e.g rvm/rvm_mobilenetv3_fp32.onnx

  • params_file – (str)Path of parameters file, 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, default is ONNX

get_profile_time()#

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

predict(input_image)[source]#

Matting an input image

Parameters

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

Returns

MattingResult

property size#

Returns the preprocess image size

property swap_rb#

Whether convert to RGB, Set to false if you have converted YUV format images to RGB outside the model, dafault true

property video_mode#

Whether to open the video mode, if there are some irrelevant pictures, set it to fasle, the default is true