contrastive-predictive-coding icon indicating copy to clipboard operation
contrastive-predictive-coding copied to clipboard

Published 20 hours ago • verified publisher icon davidtellez

Fixed seed for reproducing the results

Open JunwenBai opened this issue 4 years ago • 1 comments

Has anyone found a way (or a set of fixed random seed) to reproduce the results? I tried to fix every random seed, but it seems that there still exists randomness. Based on my experience, more than half of my runs fail to escape 0.5 accuracy, which is quite annoying. Any suggestions would be helpful! Thx!

JunwenBai avatar Jun 11 '20 05:06 JunwenBai

Has anyone found a way (or a set of fixed random seed) to reproduce the results? I tried to fix every random seed, but it seems that there still exists randomness. Based on my experience, more than half of my runs fail to escape 0.5 accuracy, which is quite annoying. Any suggestions would be helpful! Thx!

Add np.random.seed(123) in data_utils.py

943fansi avatar Jan 20 '22 04:01 943fansi