Ian8888 commented on issue #14333: Predict of mx.mod.Module api problem URL: https://github.com/apache/incubator-mxnet/issues/14333#issuecomment-470396433 > @Ian8888 Can you shed some light on the model you are using ? > Specifically, what's the last layer of your model ? Is it Sigmoid or Softmax ? > In case you want to do a binary classification, you could use the softmax layer at the end to convert the output from your model to probability values, and based on that you can predict the class as being x or y ( Or 0 or 1 in your case ). > > @mxnet-label-bot Add [Python, Question] > @Ian8888 Can you shed some light on the model you are using ? > Specifically, what's the last layer of your model ? Is it Sigmoid or Softmax ? > In case you want to do a binary classification, you could use the softmax layer at the end to convert the output from your model to probability values, and based on that you can predict the class as being x or y ( Or 0 or 1 in your case ). > > @mxnet-label-bot Add [Python, Question] The last layer is softmax. I tried using data.label to get the label information. Hope, the softmax result has mapping the label information.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services