Chapter 3 - Tensorflow steps

[AunCly]

Hello,

I don't know if it's an error, or if i missunderstand, but in training_step method

loss = mean_squared_error(predictions, targets)

And loss method take params in wrong (i supposed) order

def mean_squared_error(targets, predictions):

In any case thanks a lot for the free book !

[moghalis]

Hello AunCly. Order has no damage here in calculating the loss mathematically as error between MSE(predictions, targets)= MSE (target, predictions). Regards

…

On Thu, Oct 23, 2025 at 11:23 AM Aurélien Clugery ***@***.***> wrote: *AunCly* created an issue (fchollet/deep-learning-with-python-notebooks#262) <#262> Hello, I don't know if it's an error, or if i missunderstand, but in training_step method loss = mean_squared_error(predictions, targets) And loss method take params in wrong (i supposed) order def mean_squared_error(targets, predictions): In any case thanks a lot for the free book ! — Reply to this email directly, view it on GitHub <#262>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AFB5QRCPGWDHH4OHLNIFTZD3ZDXGFAVCNFSM6AAAAACKAUGE5WVHI2DSMVQWIX3LMV43ASLTON2WKOZTGU2DKMJZGU4TCNQ> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

-- Mohamed Almoghalis