tpzou
tpzou
为什么验证集正确率总是高于训练集,这难道没有问题吗?
Hi, I recently purchased an external GPU, specifically the GIGABYTE Aorus GTX 2080ti Gaming Box to use with my laptop, I have a Dell G5 RTX2060 running Ubuntu 20.04. And...
Hi Okan, Interesting work! I try to use your model in the application. But my RGBD camera is **realsense**, which depth picture seems different from yours. So, would you please...
Hi, @shunsukesaito. I am trying to follow your amazing work. However, I encountered some problems with the evaluation. Would you mind releasing the Evaluation and Metric Code of Table 1...
您好,我想询问一下关于初始化训练SDF_Net的问题。 在我尝试使用SDF网络构建我自己的网络的过程中,我发现SDF的网络在预训练的时候只对非表面进行了normal的约束,我想试试加入真值的SDF的loss  如上图,在不加非表面点的真值SDF的时候单纯重建smpl是正常的  但在加入真值后很会变得很奇怪 我的代码如下  第一个kaolin计算点是不是在Mesh内,第二个kaolin公式算点到mesh的距离 我也尝试了使用DeepSDF的clamp loss,同样会出现以上问题,这让我很难以理解,想咨询一下这是可能是什么原因所导致的?
Hi,I find the .txt file of the embryo don't seem to match with the image file. The expression in .txt is "/3/9148_7.png", while the expression in the image file is...