acia.segm.output#

Functionality for creating outputs (export) the segmentation information

class acia.segm.output.DatasetExporter[source]#

Bases: object

Base class for dataset exporters

__init__()[source]#
add(item)[source]#
Parameters:

item (ImageRoISource | list[ImageRoISource])

class acia.segm.output.MMSegmentationDataset[source]#

Bases: DatasetExporter

MMSegmentation dataset exporter

__init__(labels=None, label_coverter=<function MMSegmentationDataset.<lambda>>)[source]#
write(base_folder='data', mode='train')[source]#
Parameters:

base_folder (str | Path)

acia.segm.output.no_crop(frame, _)[source]#
Parameters:
acia.segm.output.renderVideo(imageSource, roiSource=None, filename='output.mp4', framerate=3, codec='vp09', scaleBar=None, draw_frame_number=False, cropper=<function no_crop>, filter_contours=<function <lambda>>, cell_color=(255, 255, 0))[source]#

Render a video of the time-lapse.

Parameters:

  • imageSource (ImageSequenceSource) – Your time-lapse source object.

  • roiSource ([type]) – Your source of RoIs for the image (e.g. cells). If None, no RoIs are visualized. Defaults to None.

  • filename (str, optional) – The output path of the video. Defaults to ‘output.mp4’.

  • framerate (int, optional) – The framerate of the video. E.g. 3 means three time-lapse images per second. Defaults to 3.

  • codec (str, optional) – The video format codec. Defaults to “vp09”.

  • scaleBar (ScaleBar, optional) – The scale bar object. Defaults to None.

  • draw_frame_number (bool, optional) – Whether to draw the frame number. Defaults to False.

  • cropper ([type], optional) – The frame cropper object. Defaults to no_crop.

acia.segm.output.fast_mask_rendering(masks, im, colors, alpha=0.5)[source]#

Plot masks on image.

Parameters:

  • masks (tensor) – Predicted masks on cuda, shape: [n, h, w]

  • colors (List[List[Int]]) – Colors for predicted masks, [[r, g, b] * n]

  • im_gpu (tensor) – Image is in cuda, shape: [3, h, w], range: [0, 1]

  • alpha (float) – Mask transparency: 0.0 fully transparent, 1.0 opaque

  • retina_masks (bool) – Whether to use high resolution masks or not. Defaults to False.

acia.segm.output.fast_mask_rendering_torch(masks, im, colors, alpha=0.5)[source]#

Plot masks on image.

Parameters:

  • masks (tensor) – Predicted masks on cuda, shape: [n, h, w]

  • colors (List[List[Int]]) – Colors for predicted masks, [[r, g, b] * n]

  • im_gpu (tensor) – Image is in cuda, shape: [3, h, w], range: [0, 1]

  • alpha (float) – Mask transparency: 0.0 fully transparent, 1.0 opaque

  • retina_masks (bool) – Whether to use high resolution masks or not. Defaults to False.