what is evaluate method in tensorflow #352
-
Hi! I am newbie to machine learning and right now i am struggling to understand the evaluate method. model.evaluate() |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
Hey @PriyankaSharma0925, The This means asking the question "how well is our model doing?" When fit a model to a dataset (using When we call For example, a model will fit on training data: And then we will evaluate it on testing data (data it has never seen before): We evaluate to see how well the patterns it learned on the training data generalize to unseen data. |
Beta Was this translation helpful? Give feedback.
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.