I would like to use PredictorMeasurements on the result of NetTrain, but it says it expects a PredictorFunction object. So apparently, the output of NetTrain is not a PredictorFunction.
Am I right? If so, can this be done?
Thanks
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
2
In Mathematica 11.1 you can convert your network only into a ClassifierFunction. I expect that converting into a PredictorFunction will be added in the next releases.
net = NetChain[
{100, 2, SoftmaxLayer[]},
"Input" -> 100,
"Output" -> NetDecoder[{"Class", {0, 1}}]
]
SeedRandom[0];
X = RandomReal[{-1, 1}, {1000, 100}];
Y = RandomInteger[1, 1000];
net = NetTrain[net, X -> Y, MaxTrainingRounds -> 1]
c = Classify[net]
UPDATE
Yes, it's possible.
answered Mar 15, 2017 at 6:23
-
$\begingroup$ Any idea how to ensure that a net is evaluated with a GPU when applying
ClassifierMeasurements? Takes forever with a CPU... $\endgroup$– dan7geoCommented Jun 5, 2017 at 6:21 -
$\begingroup$ @dan7geo I don't know. Sorry. $\endgroup$ Commented Jun 5, 2017 at 12:35