Join GitHub today
GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.
Sign upGitHub is where the world builds software
Millions of developers and companies build, ship, and maintain their software on GitHub — the largest and most advanced development platform in the world.
Loss function result differs from training Loss #30
Comments
jklanger
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Loss evaluated with a separate function:
let lossFn = mi.Func<single> (loss) |> arg2 input targetdiffers from the loss evaluated during training:
let trainFn () = Train.train trainable fullDataset trainCfgWhen thisoption ist set:
SymTensor.Debug.DisableCombineIntoElementsOptimization <- truethe results are consistent again!
Tested via DeepPrivate:
Z:\DeepPrivate\****Models\bin\Release\****Models.exe Z:\DEVELOP\DeepPrivate\****Models\cfgs\COPYING\LSTM\80reluOutputTest\Config.fsxCode during training gets optimized differently?
Tested with [band 2277e5e]