Ray

Results 9 comments of Ray

Seems table 1 is taking 3 digits but the CD I got form the output csv file looks a little bit weird from table 1 (a) oflow row

![image](https://user-images.githubusercontent.com/26106300/126751660-e232a244-865f-4d40-abbf-c741c545cedc.png) According to the paper, OFlow refer to ONet for metric discription, I guess you us Chamfer-L1 in table.1 right? Not this "chamfer" in the output csv? I add the...

to some reason, the state I sent to the ODE is about 786,432 dim

The yellow one is GT, the red one is from depth ![Screenshot from 2020-08-31 17-36-12](https://user-images.githubusercontent.com/26106300/91706285-c4fe6800-ebb0-11ea-9501-05cf9715d57e.png) ![Screenshot from 2020-08-31 17-36-30](https://user-images.githubusercontent.com/26106300/91706298-c92a8580-ebb0-11ea-8e93-441439b20a8c.png)

This is the render results, it's an airplane ![Screenshot from 2020-08-31 17-39-53](https://user-images.githubusercontent.com/26106300/91706592-2c1c1c80-ebb1-11ea-853a-4e32dfc47596.png)

The same problem appears to me, there are 3 issues for the invalid memory now, and none of them can work out... could someone help? thanks!

Same problem, this is indeed the bigest issue for using this project

I solved this issue (at least i can inference) by using the latest mmcv and mmsegmentation and modify the code in this repo, at least i guess for now the...