On 04-10-16 23:47, Yuandong Tian wrote: > Hi all, > > DarkForest training code is open source now. Hopefully it will help the > community. > > https://github.com/facebookresearch/darkforestGo > <https://github.com/facebookresearch/darkforestGo> > > With 4 GPUs, the training procedure gives 56.1% top-1 accuracy in KGS > dataset in 3.5 days, and 57.1% top-1 in 6.5 days (see the simple log > below). The parameters used are the following: --epoch_size 256000 --GPU > 4 --data_augmentation --alpha 0.1 --nthread 4
It's probably due to my unfamiliarity with Torch but I couldn't find where the actual network structure is defined. I think the script runs with alpha=0.05, not alpha=0.1. I understood from previous comments you didn't find momentum to be beneficial. This highly surprises me. Is that still the case? -- GCP _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
