We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
在计算anchor和true_box的iou时(train.py文件第107行开始),用到了归一化的true_boxes尺寸(在train.py的81和82行),但是anchor却没有进行归一化就与true_box进行的iou计算,从而来判断true_box属于哪个anchor,这肯定是有问题的,一个数值很大,一个只有0-1范围,从而导致anchor不能正确匹配,我是在单步调试过程中发现。不知道up主怎样认为
The text was updated successfully, but these errors were encountered:
再看看计算iou用的到底是哪个量
Sorry, something went wrong.
计算iou用的就是没有归一化的anchors和归一化后的true_box呀,anchor是通过get_anchors()函数得到的,期间没有经过归一化处理,但是anchor.txt中的anchors是根据真实图片设定的anchors,如有遗漏没看到地方望up主指点
你print一下吧。 intersect_mins = np.maximum(box_mins, anchor_mins) intersect_maxes = np.minimum(box_maxes, anchor_maxes)
No branches or pull requests
在计算anchor和true_box的iou时(train.py文件第107行开始),用到了归一化的true_boxes尺寸(在train.py的81和82行),但是anchor却没有进行归一化就与true_box进行的iou计算,从而来判断true_box属于哪个anchor,这肯定是有问题的,一个数值很大,一个只有0-1范围,从而导致anchor不能正确匹配,我是在单步调试过程中发现。不知道up主怎样认为
The text was updated successfully, but these errors were encountered: