Fabio Cermelli
Fabio Cermelli
Ciao @roysubhankar, Sorry for the late answer. Actually, I started using the background class after the last Continual SemSeg papers, that are using the background for the All class. However,...
Hello @Sreeni1204, 1) Yes, the model is the same. However, the performance is reported after the last incremental step is done. Thus, doing one incremental step or doing multiple give...
Hello @CuongHoang86. So, from the console error, it seems the issue arises with tensorboardX. Can you try to use torch.tensorboard instead? It has the same interface, so you only need...
Hi @Ailice0! Did you get any errors? How long it takes to conclude the process? Which version of python/pytorch are you using?
Ok, the strange thing is that it's not outputting anything... If it crashes, I'd expect at least an error message 😅 Maybe try this: logging.basicConfig(filename=filename, level=logging.INFO, format=f'%(levelname)s:{rank}: %(message)s', force=True) in...
Hello. Please refer to this repository for the install instruction: https://github.com/mapillary/inplace_abn
It seems you have trouble compiling their library. Can you please check if the CUDA and GCC you are using match the requirement? Did you try to install the library...
Take a look at Mibv2 here: https://github.com/fcdl94/MiBv2/
Inplace-abn installation is not under my control 😅 Please if you are not able to install it, check their repository. In-place ABN is mandatory for the project, there is no...
It was CUDA 10.2.