Yes, I first convert the compact RLE to a masked array: import pycocotools.mask as mask maskedArr = mask.decode(compactRLESegmentation) then convert this to polygon format def polygonFromMask(maskedArr): # https://github.com/hazirbas/coco-json-converter/blob/master/generate_coco_json.py co...
I want to create a new dataset same as coco format, and now I have converted mask binary image to RLE format by using encode function in mask.py. But I don't know how to convert mask binary image or RLE format to polygon format, someone can help me? Thanks in advance. 👍 7 wasp...
Could you please share the function that converts masks to polygons, which you used to generate the segmentation annotations for COCO dataset? Because I would like to train the deepMask on my dataset, which needs to represent masks by polygons to generate the groundtruth. ...