jucic
jucic
我跑第七章pnp和icp的时候就报double free or corruption了
只装了一个版本的g2o，网上查这错误说是指针什么的内存被重复释放？检查了代码好像没这种问题，摸不着头脑。。
只是运行./pose_estimation_3d2d命令行参数不给全也是报这个错误，而不是提示"usage:./pose_estimation_3d2d img1 img2 depth1 depth2"的错误，很奇怪了。
I have the smae problem, have you made it real-time?
> I do not use onnx as an intermediate step but define a TRT model directly. How to define a TRT model directly? by torch2tensorRT?
> Dear all, this is because of the normalization issue, this flow_norm can solve all your problem: [tomrunia/OpticalFlow_Visualization#7](https://github.com/tomrunia/OpticalFlow_Visualization/pull/7) oh my god! Thanks a lot! I can't beleive this simple problem...
I encountered with the same problem > Hi, i believe this problem **_is general_** in **_stereo senario._** But there's nothing to do with the stereo matching algorithms. > > Note...
> Hi, I have been trying to export DPT-Hybrid to onnx today using the dpt_scriptable branch and also encountered `RuntimeError: NYI: Named tensors are not supported with the tracer`. I...
I update the code by adding the get_transform() function and the result seems right now!  