Currently numpy is unseeded so all random function using it are not repeatable. The expectation is that the seed will be used for Torch and Numpy so that experiments will have identical results with the same seed.
Also linked to enhancement request of resume option to provide access to saved file and perform a different kind of optimization than the original experiment.
Currently numpy is unseeded so all random function using it are not repeatable. The expectation is that the seed will be used for Torch and Numpy so that experiments will have identical results with the same seed.