Skip to content

what is evaluate method in tensorflow #352

Discussion options

You must be logged in to vote

Hey @PriyankaSharma0925,

The model.evaluate() method evaluates a model.

This means asking the question "how well is our model doing?"

When fit a model to a dataset (using model.fit()) it learns patterns in that data.

When we call model.evaluate() we're asking, how good are those patterns the model learned in the data.

For example, a model will fit on training data: model.fit(X_train, y_train)

And then we will evaluate it on testing data (data it has never seen before): model.evaluate(X_test, y_test)

We evaluate to see how well the patterns it learned on the training data generalize to unseen data.

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@PriyankaSharma0925
Comment options

Answer selected by PriyankaSharma0925
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants