Thomas Germer
Thomas Germer
I had the same error with Python 3.12, but Python 3.10 worked. But I still had to build from source anyway because the distribution was compiled for a different processor...
The original authors report results for the V100 GPU. The results I report here are for A100 and P100 GPUs, because that is what I have access to. The V100...
Which running time do you get? For me, the first batch takes one second longer than the others, but after that it is fairly stable. If you want to exclude...
> Did you experience the training time difference when using different Pytorch versions? I have not tested different versions, but I think that the version of cuDNN is even more...
Glad that you found it useful! And thank you for the results on a V100 GPU. I'll add them to the README right away.
Just a quick update: The PyTorch version of our server has been upgraded recently and the results for the A100 GPU are now over twice as fast, probably because the...
Thank you, fixed!
Yeah, I think so.
https://www.mathematik.uni-marburg.de/~eyke/publications/tfs11_draft.pdf might be interesting. Or maybe there is something interesting among those papers:  
I implemented the methods based on a lecture where the citations were somewhat terse: * PC: Bez74 * NPC: Bac78, Rou78, Dav96 * FHV: GG89 * FS: FS89 * XB:...