How to map softMax output to labels in MXNet

Question

In Deep learning the predictions are often encoded using one hot vector. I am using MXNet for creating a simple Neural Network which classifies images of animals as cats,dogs,horses etc. When I call the Predict method of MXNet it returns me a softmax output. Now, how do I determine that the index of the entry in the softmax output corresponding to maximum probability is Cats or Dogs or Horses. The softmax output only gives an array without any mapping of the results with the corresponding label.

Answer 1

This might help answering your question. http://mxnet.io/tutorials/python/predict_imagenet.html https://github.com/dmlc/mxnet-notebooks/blob/master/python/how_to/predict.ipynb

This example uses pretrained model to predict images and synset dataset.