dbolya
commented
4 years ago If you want a graphical display, you can simply use --display when evaluating. If you want to export those masks, you can use --output_coco_json when evaluating (which I see you've already done to get those numbers). That will output a json with all the masks in it in the results/ directory. They're in COCO's RLE format though, so you'll need pycocotools to decode it.
And those numbers are COCO's metrics. Check out the COCO dataset for more details.
hello,how to get the position coordinates of the object after segmentation? Is there any graphical display interface result after segmentation? By the way, what do these mean？ Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.745 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.941 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.903 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.730 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.744 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.769 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.837