Kaidong Zhang
Kaidong Zhang
Switch to gcc/g++ 5.5 version, and try it again.
I encountered the same problem as you, there are lots of warnings and errors shown in the terminal, maybe it's caused by the mismatch of gcc/g++ version? I don't know...
Sorry for the late reply. We are interested in adding FGT to Hugging Face, and I will add this thing to my todo list.
Please read issue #17
Thanks for your recommendation, I will consider this technology during my spare time.
@houtianze I have tried your instructions many times, but things cannot get improved. It seems there is something wrong with your server, do you have another solution to this problem?
Thanks for your kindly help, authorization is successful, but my python raises an HTTPError, maybe the remote server is blocked by the Great Wall. Anyway, I really appreciate your fantastic...
Currently, we don't plan to release the training code, but may upload that someday. The training code of ISVI is quite similar to [FGT](https://github.com/hitachinsk/FGT), you can modify the training code...
I use the moving square mask with continuous motion trace. And I used them in the quantitative results.
Hello, as far as I know, ISVI should not take so much time during inference. Please check the CUDA compilation of the Forward_warp package.