我能够通过运行model_main.py
成功地训练我的模型,并得到以下结果:
平均精度(AP)@ [IoU = 0.50:0.95 |面积=全部| maxDets = 100] = 0.344
平均精度(AP)@ [IoU = 0.50 |面积=全部| maxDets = 100] = 0.514
平均精度(AP)@ [IoU = 0.75 |面积=全部| maxDets = 100] = 0.376
平均精度(AP)@ [IoU = 0.50:0.95 |面积=小| maxDets = 100 ] = 0.112
平均精度(AP)@ [IoU = 0.50:0.95 | area = medium | maxDets = 100 ] = 0.317
平均精度(AP)@ [IoU = 0.50:0.95 |面积=大| maxDets = 100 ] = 0.504
平均召回率(AR)@ [IoU = 0.50:0.95 |面积=全部| maxDets = 1 ] = 0.303
平均召回率(AR)@ [IoU = 0.50:0.95 |面积=全部| maxDets = 10 ] = 0.474
平均召回率(AR)@ [IoU = 0.50:0.95 |面积=全部| maxDets = 100 ] = 0.509
平均召回率(AR)@ [IoU = 0.50:0.95 |面积=小| maxDets = 100 ] = 0.222
平均召回率(AR)@ [IoU = 0.50:0.95 | area = medium | maxDets = 100 ] = 0.507
平均召回率(AR)@ [IoU = 0.50:0.95 |面积=大| maxDets = 100 ] = 0.676
我们如何解释这一点? area
代表什么? mAP值在哪里?
答案 0 :(得分:0)
部分答案(区域,mAP)可以在此帖子中找到:
您的“平均召回(AR)@ [IoU = 0.50:0.95 | area = all | maxDets = 1]”对应于答案中的“ DetectionBoxes_Recall / AR @ 1”。