-
Notifications
You must be signed in to change notification settings - Fork 26
New issue
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
BlendedMVS数据集评估结果 #37
Comments
论文 Table3 中给出的 EPE e1 和 e3 是在 BlendedMVS 的 validation set 上得到的。 |
非常感谢您(wtyuan96)热心回复,谢谢您为我解惑。我还有一个疑问,按照您说的,那根据我的输出日志“less1 = 0.801,less3 = 0.916”来看的话我的 e1和e3分别是80.1%和91.6%,和原文中给出的8.32%和3.62%差距实在太大,因为我的模型在dtu上精度较为接近作者的得分,但在blendedMVS上的评估结果几乎相差一个数量级。请问我原工程中打印日志输出的结果是否为百分数呢? |
我也很疑惑,实际上从作者论文里面所述,e1和e3是大于1个像素和3个像素的误差百分比,所以是越低越好,而作者的代码实现里面则是小于1个像素和3个像素的误差的百分比,less1和less3和论文里面提到的e1和e3刚好反过来了 |
你好,我也遇到了这个问题,我想请问一下你最后是怎么解决的呢 |
非常感谢作者的伟大无私奉献,在论文学习过程中我遇到一个疑问,希望能够得到作者的解答,感谢之前问题中作者的不吝赐教。
在对blendedMVS数据集评估时,论文Table 3 里给出的 EPE e1 和 e3如何得出的呢?是根据微调时输出的结果得出的吗?如下打印日志,怎么和这三个值“EPE e1 和 e3”对应起来呢?希望能够得到作者回复,感谢!
Epoch 0/16, Iter 0/16902, lr 0.000067, train loss = 11.082, depth loss = 0.013, epe = 5.510, less1 = 0.657, less3 = 0.837, time = 5.783
Epoch 0/16, Iter 50/16902, lr 0.000080, train loss = 7.146, depth loss = 0.007, epe = 2.446, less1 = 0.801, less3 = 0.916, time = 1.190
The text was updated successfully, but these errors were encountered: