本文介绍了在YOLOv5训练过程中，如何根据数据集自适应地调整Anchors的过程。通过计算Best Possible Recall (BPR)，然后运用k-means和遗传算法优化，最终找到适合当前数据集的Anchors，提高目标检测的性能。训练结果显示，经过算法优化后的Anchors能够更好地适应不同尺寸的对象，并保存到模型中供后续使用。
在进行yolov5训练的时候，会输出：
Analyzing anchors... Best Possible Recall (BPR) = 0.8838. Attempting to generate improved anchors, please wait...
WARNING: Extremely small objects found. 2274 of 14719 labels are < 4 pixels in width or height.
Running kmeans for 9 anchors on 14700 points...
thr=0.25: 0.9927 best possible recall, 5.10 anchors past thr
n=9, img_size=480, metric_all=0.348/0.766-mean/best, past_thr=0.515-mean: 10,3, 18,6, 24,12, 36,16, 42,28, 62,39, 77,68, 110,49, 121,100
Evolving anchors with Genetic Algorithm: fitness = 0.7855: 100%|████████████| 1000/1000 [00:02<00:00, 484.50it/s]
thr=0.25: 0.9972 best possible recall, 5.23 anchors past thr
n=9, img_size=480, metric_all=0.358/0.785-mean/best, past_thr=0.524-mean: 11,2, 16,5, 22,8, 28,12, 36,18, 44,28, 62,39, 79,64, 117,96
New anchors saved to model. Update model *.yaml to use these anchors in
最低0.47元/天 解锁文章
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
