Romain Goussault

Hello @Martiniann, the issue you have is that you are trying to connect to deployed Substra platform at `http://substra-backend.node-1.com` which does not exist. There are three solutions: - Use an...

Hello @bdqnghi it is still not possible to do unsupervised learning with the current Substra. We still plan to add this feature at some point but we are not there...

Results for seqavg from an old notebook: https://github.com/SubstraFoundation/distributed-learning-contributivity/blob/master/saved_experiments/mnist_cifar10_distributed_learning/mnist_cifar10_distributed_learning.ipynb  Random split used to work very well but performance on stratified split was very poor.

We have decided to remove this method. To be done by @RomainGoussault

This can help: https://blog.tensorflow.org/2020/04/introducing-new-tensorflow-profiler.html?m=1

 `_make_train_function` should be investigated

Yes it would be interesting to use the tensorflow profiler : https://blog.tensorflow.org/2020/04/introducing-new-tensorflow-profiler.html?m=1

Do we have data on how much slower it is to have a small batch size vs a big batch size?

happened only once ?

http://wbec-ridderkerk.nl/html/UCIProtocol.html The move format is in long algebraic notation. A nullmove from the Engine to the GUI should be send as 0000. Examples: e2e4, e7e5, e1g1 (white short castling), e7e8q...