You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
self.predictions is the classification result. For example, if you get "1", that's equivalent to [0,1]. [1, 0, 1, 1, ...] is not possible because only one class can be predicted at a time. If you want to get the probabilities for all classes you can use self.scores and use a softmax on that.
Code:
self.predictions = tf.argmax(self.scores, 1, name="predictions")
But, I want to get the classification result, such as [1, 0, 1, 1, ...], How to get it?
Thank you!
The text was updated successfully, but these errors were encountered: