test results

[Youggie]

Is there anyone got the Similar results to the original paper on the coco dataset？why I can't get a better result？

[gonghaotian]

Is there anyone got the Similar results to the original paper on the coco dataset？why I can't get a better result？

HI~ what's ur mAP result? the mAP with single scale in paper is 40.6 while mine is 38.0. I think the difference is acceptable. However, I test the trained weight from this paper. the mAP is higher than the result in paper. btw,I set the batchsize to 29 with 6 gpu,because I dont have enough GPU as the paper to set batchsize to 49. My result and the tested result are shown as follow:

test result with trained weight: Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.596 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.772 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.647 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.335 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.649 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.772 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.440 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.671 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.719 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.530 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 ] = 0.885

test result with my trained weight: Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.380 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.534 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.402 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.166 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.397 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.505 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.340 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.525 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.572 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.352 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.602 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.749

[gonghaotian]

the test result with trained weight in paper is much higher than the result in paper I could not figure out this point

[omtbreak]

Hello, I finished the test and got the result.josn, but how can I find the mAP?