Make a prediction using mxnet CNN model

Question

Hi I'm a newbie to data science, I followed this tutorial https://mxnet.incubator.apache.org/tutorials/nlp/cnn.html but I am confused over how to make a single prediction using the trained model generated by the above mentioned tutorial. Please guide me the right direction to fix this. Thanks.

Answer 1

You can load the model as depicted in the following code:

sym, arg_params, aux_params = mx.model.load_checkpoint('cnn',3)

mod = mx.mod.Module(symbol=sym, context=mx.cpu(), label_names=None)

mod.bind(for_training=False, data_shapes=[('data', (1,3,224,224))], label_shapes=mod._label_shapes)

mod.set_params(arg_params, aux_params, allow_missing=True)

Gain practical exposure with data science projects in Intellipaat's Data Science course online.