PaddleDetection的coco类型的目标检测数据集评估(Evaluation)标准

输出结果

PaddleDetection 使用coco类型的数据集，一般的输出结果如下

Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=2.61s).
Accumulating evaluation results...
DONE (t=0.74s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.245
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.424
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.264
 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 ] = 0.220
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.243
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.522
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.603
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.604
 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 ] = 0.538
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.611
[05/27 16:26:41] ppdet.engine INFO: Total sample number: 2258, averge FPS: 82.94079298317101
[05/27 16:26:41] ppdet.engine INFO: Best test bbox ap is 0.245.

实际都是根据coco数据集官方给出的指标，指标如下

在括号中 IoU=0.50:0.95代表IoU 0.5到0.95的区间每隔0.05分别计算一次AP，最终相加求平均值, area = all代表所有尺寸的检测目标，maxDets=100代表Average Call given 100 detection per image. maxDets等于多少，就是多少detection。

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.245

尺寸判定条件

尺寸	判定条件
small	尺寸小于32x32个像素
medium	尺寸大于，32x32个像素，小于96x96个像素
large	尺寸大于96x96个像素