2

I was able to successfully train my model by running model_main.py and got this result:

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.344

Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.514

Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.376

Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.112

Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.317

Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.504

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.303

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.474

Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.509

Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.222

Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507

Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.676

How do we interpret this? What does area represent? Where is the mAP value?

Chaine
  • 1,368
  • 4
  • 18
  • 37
  • I would like to know the same. Going by these small numbers how was your result quality? What are the state of the art numbers supposed to be? – physicist Jan 12 '19 at 00:28

1 Answers1

1

Part of the answer (area, mAP) can be found in this post here:

Tensorboard graph recall

Your "Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ]" corresponds to "DetectionBoxes_Recall/AR@1" in the answer there.

ktii
  • 59
  • 7