Replies: 1 comment
-
Hey @respwill, They'll be very similar with their results. Though because of the randomness of machine learning, you might find slightly different results between two of the same models trained on the same data. Though you can try to prevent the differences by setting random seeds. Such as: tf.random.set_seed(42)
np.random.seed(42)
model = ...
model.compile()
model.fit() |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I just finished Q1 of Exercise 8.
All of results shows that Functional API model is slightly better than Sequential API. (e.g. f1 score is 0.01 higher)
I printed summary of each model and compared them.
Structure and number of parameters are same, so I think I built each models properly.
I wonder if my conclusion is right.
Functional API is usually better than Sequential API??
Beta Was this translation helpful? Give feedback.
All reactions