Open le-dawg opened 4 years ago
Have you tried tf.estimator.BinaryClassHead()
? I believe it uses the same loss under the hood, specifically sigmoid_cross_entropy
.
Well, I figured that out in the meantime.
But a problem persists:
BinaryClassHead
It uses the correct loss but when I predict using a simple_dnn AdaNet of three iterations via estimator.predict()
the network always predicts with class 0.
The same head works on the canned tf.estimator.LinearClassifier
which I would suspect to be a problem regarding an incorrect loss function. I can't troubleshoot the AdaNet estimator any deeper than this. I will take any help I can!
Hi all,
I seek to optimize an ensemble for binary classification. My established baseline uses the
binary_crossentropy
loss provided bykeras
. Using the same notation yieldsunsupported callable
, because it seems thebase_head.Head()
does not tie into the default tf implementation.What can I do train with the binary crossetropy?