Visaulize(可视化)#

fastdeploy.vision.vis_detection#

class fastdeploy.vision.vis_detection(im_data, det_result, labels=[], score_threshold=0.0, line_size=1, font_size=0.5)[source]#

Show the visualized results for detection models

Parameters

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

  • det_result – the result produced by model

  • labels – (list of str) the visualized result will show the bounding box contain class label

  • score_threshold – (float) score_threshold threshold for result scores, the bounding box will not be shown if the score is less than score_threshold

  • line_size – (float) line_size line size for bounding boxes

  • font_size – (float) font_size font size for text

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_segmentation#

class fastdeploy.vision.vis_segmentation(im_data, seg_result, weight=0.5)[source]#

Show the visualized results for segmentation models

Parameters

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

  • seg_result – the result produced by model

  • weight – (float)transparent weight of visualized result image

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_keypoint_detection#

class fastdeploy.vision.vis_keypoint_detection(im_data, keypoint_det_result, conf_threshold=0.5)[source]#

Show the visualized results for keypoint detection models

Parameters

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

  • keypoint_det_result – the result produced by model

  • conf_threshold – (float) conf_threshold threshold for result scores, the bounding box will not be shown if the score is less than conf_threshold

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_face_detection#

class fastdeploy.vision.vis_face_detection(im_data, face_det_result, line_size=1, font_size=0.5)[source]#

Show the visualized results for face detection models

Parameters

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

  • face_det_result – the result produced by model

  • line_size – (float) line_size line size for bounding boxes

  • font_size – (float) font_size font size for text

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_face_alignment#

class fastdeploy.vision.vis_face_alignment(im_data, face_align_result, line_size=1)[source]#

Show the visualized results for face alignment models

Parameters

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

  • face_align_result – the result produced by model

  • line_size – (float)line_size line size for circle point

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_matting#

class fastdeploy.vision.vis_matting(im_data, matting_result, transparent_background=False, transparent_threshold=0.99, remove_small_connected_area=False)[source]#

Show the visualized results for matting models

Parameters

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

  • matting_result – the result produced by model

  • transparent_background – whether visulizing matting result with transparent background

  • transparent_threshold – since the alpha value in MattringResult is a float between [0, 1], transparent_threshold is used to filter background pixel

  • remove_small_connected_area – (bool) if remove_small_connected_area==True, the visualized result will not include the small connected areas

Returns

(numpy.ndarray) image with visualized results

fastdeploy.vision.vis_ppocr#

class fastdeploy.vision.vis_ppocr(im_data, det_result)[source]#

Show the visualized results for ocr models

Parameters

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

  • det_result – the result produced by model

Returns

(numpy.ndarray) image with visualized results