sidhomj/DeepTCR

Reproducible clustering

emm1R opened this issue · 5 comments

emm1R commented

Hi,
Is there a way to make the training and clustering reproducible? Setting graph_seed and split_seed in Train_VAE does not seem to do the trick.

sidhomj commented

What are you using to do the clustering? Your own algorithm or the clustering method in DeepTCR?

emm1R commented

The clustering method in DeepTCR.

sidhomj commented

The default method to cluster is the phenograph algorithm, which I do not believe is a deterministic algorithm. You can read more about it here: https://github.com/jacoblevine/PhenoGraph

emm1R commented

Is the training then deterministic if the two seeds are given values?

sidhomj commented

From what I have seen, if the training is done with a GPU, it will never be perfectly deterministic. Some of the gpu tensorflow ops are not deterministic so there can be minor differences from training session to session.