Search code examples
azureazure-machine-learning-service

Incorrect neural network schema in training output

I'm training a model in Azure ML Studio and the Net# specification I'm using doesn't match the NET# specification in the training output.

Here's my experiment - enter image description here

and here are my NN params -

enter image description here

and finally here is the NET# specification in the Hyperparams output -

enter image description here It's not using two hidden layers and it's also using sigmoid instead of ReLu. Is this expected behavior?

Thanks!

Solution

  • There is an issue with using custom NET# and parameter sweeps together: it switches over to using the default fully connected topology.

    Unfortunately, the workaround is to train the model for each parameter value separately.

    -Roope