在YOLO1之后,在其他迭代中使用锚固箱有一段时间的趋势(我相信原因是要加快训练并更好地检测到不同尺寸的对象)
,但是Yolov1具有有趣的机制,其中有k个界限的数量盒子预测器滑动每个网格单元,以便能够专门检测不同的缩放对象。
女士们,先生们,这是我想知道的:
在训练时间很长的情况下,与Yolov9000或依赖于锚固盒机构的Yolov9000或其同行相比,Yolov1中的这些边界预测变量可以实现更好的边界盒
After YOLO1 there was a trend of using anchor boxes for a while in other iterations as priors (I believe the reason was to both speed up the training and detect different sized objects better)
However YOLOV1 has an interesting mechanism where there are k number of bounding box predictors sliding each grid cell in order to be able to specialize in detecting different scaled objects.
Here is what I wonder, ladies and gentlemen:
Given a very long training time, can these bounding box predictors in YOLOV1 achieve better bounding boxes compared to YOLOV9000 or its counterparts that rely on anchor box mechanism
发布评论
评论(1)
根据我的经验,他们可以。我观察到了两种可能的优化路径,其中之一已经在最新版本的Yolov3和v5中实现了( https:/> https:/ /Github.com/ultralytics/yolov5 )
我观察到的是,对于Yolov3,即使在训练之前,使用K使用K表示聚类,我们可以确定许多``common box''形状。当锚屏蔽作为“特定”数据集的hador屏蔽中馈入网络时,这些数据确实提高了Yolov3网络的性能头。据我所知,这项技术是在其边界框回归代码的最新迭代中实现的。
抑制某些层。在Yolov3中,网络在三个阶段进行检测,其想法是逐步检测到较小对象的较大对象。 Yolov3(在理论上V1)可以通过某些反复试验而受益,您可以根据您在步骤1中发现的公共边界框形状来确定网络更喜欢使用网络。
。
。
In my experience, yes they can. I observed two possible optimization paths, one of which is already implemented in latest version of YOLOV3 and V5 by Ultralytics (https://github.com/ultralytics/yolov5)
What I observed was that for a YOLOv3, even before training, using a K means clustering we can ascertain a number of ``common box'' shapes. These data when fed into the network as anchor maskes really improved the performance of the YOLOv3 network for "that particular" dataset since the non-max suppression routine had much better chance of succeeding at filtering out spurious detection for particular classes in each of the detection head. To the best of my knowledge, this technique was implemented in latest iterations of their bounding box regression code.
Suppressing certain layers. In YOLOv3, the network performed detection in three stages with the idea of progressively detecting larger objects to smaller objects. YOLOv3 (and in theory V1) can benefit if with some trial and error, you can ascertain which detection head is your network preferring to use based on the common bounding box shapes that you found in step 1.