Weird LogisticRegressionOutput Bug #1975
Comments
you need to change num_hidden to 1 |
Odd for a number of reasons:
What should be the labels for binary classification? Is it 0 and 1, 1 and 2 or -1 and 1 if I use recordio, or the built-in ImageRecordIter |
I have the same issue here. If I change the output activation function to logistic regression and change the num of hidden units ( here they are essentially the number of outputs) to the same as my label, the model is able to run. When there is only one output, you leave the second dimension empty. For example, import mxnet as mx val_training = mx.random.normal(0, 1, (5, 5)) data = mx.symbol.Variable('data') model = mx.model.FeedForward( model.fit(X = train_iter) |
Whenever I swap out SoftmaxOutput for LogisticRegressionOutput,
I get this error,
There is not much examples on binary classification using mxnet, is this correct in how I use LogisticRegressionOutput?
The text was updated successfully, but these errors were encountered: