I am training a NN with some synthetic data. I was running everything on REPL and things were going on the right direction, but when I tried to wrap my code inside a function() to use custom training loops, my model(x) started to return the same output every iteartion, as it would have stopped up…

Probably has to do with your loss(x, y) definition. I suspect the m in the function body is not referencing the m created inside all_the_code and instead referencing some other m in global scope. In any case, it is better to explicitly pass in the model to the loss function, because depending on the…

Training gets differents results when using Flux.train() inside function

Specific Domains Machine Learning

german_brunini August 23, 2020, 11:01pm 3

@darsnack, You nailed it. Thank you very much. Now it run like it’s supposed to!.

Topic		Replies	Views
Flux training GPU vs CPU different results Machine Learning gpu , flux	7	1212	August 20, 2020
Params not getting updated during training New to Julia flux	25	1848	October 11, 2020
Getting gradients with loss using for-loop is slow in Flux.jl Machine Learning	4	307	August 7, 2023
Train flux struct with list of models General Usage flux	8	423	March 31, 2023
Flux.jl is not modifying the loss Machine Learning	4	825	June 25, 2019

Training gets differents results when using Flux.train() inside function

Related topics