lrxjason

The problem is the 32 bits system. After I change to 64 bits system, there is no error.

请问你找到解决办法了么？

谢谢你的回复。 我是在训练的时候把data里的path换位置。效果就是在论文里面上面分支是RGB，下面是IR。我如果反过来，上面是IR，下面是RGB，训练结果应该是一样的。但是，实际情况是IR在上面比RGB在上面结果好。 我分析原因是你用的上面分支的label作为最后的label，IR的视野相对大一些，所以换过来效果会好。不知道理解的对不对。 直接用训练好的换过来肯定不行呀。。。

How long to train the EuRoc dataset? Firstly, I try VINet and I found it difficult to converge than I try the DeepVo. It also can't converge. The loss function...

@HTLife I use this https://github.com/sladebot/deepvo/tree/master/src , but I change the training batch part. I try both the flownetS and CNN. Both of them do not converge. For the angle, I...

I try just use CNN part( ignore the LSTM part). It also doesn't converge. I will try to use the PoseNet to train the database tomorrow. I'm confused about the...