For comparing models...

[scottdstearns]

maybe comparing the weights vs the predictions...?

for k in range(0,len(model3.trainable_weights)):
print( tf.reduce_all(reloaded_model.trainable_weights[k].numpy() == model3.trainable_weights[k].numpy()))

[mrdbourke]

Hey @scottdstearns,

I haven't tried this personally, my guess is that almost all of the weights will be different (ever so slightly in some cases, larger in others).

Did you try it?

If so, what happened?

[scottdstearns]

Yes, Daniel, I did try it and it worked for - at least for the trainable weights: [image: image.png] Thanks again for all your help. Scott

…

On Fri, Jan 14, 2022 at 6:44 PM Daniel Bourke ***@***.***> wrote: Hey @scottdstearns <https://github.com/scottdstearns>, I haven't tried this personally, my guess is that almost all of the weights will be different (ever so slightly in some cases, larger in others). Did you try it? If so, what happened? — Reply to this email directly, view it on GitHub <#317 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXGJJIIIMQDPW2AWBVBZUMDUWCYOZANCNFSM5LSBEJDQ> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: <mrdbourke/tensorflow-deep-learning/repo-discussions/317/comments/1972758@ github.com>