How to use SqueezeNet in CNTK?

Question

I am a CNTK user. I use AlexNet but would like a more compact NN -- so SqueezeNet seems to be of interest. Or does someone have some other suggestion? How do CNTK users deploy when size matters? Does somebody have a CNTK implementation of SqueezeNet?

Answer 1

The new ONNX model format now has several pretrained vision models, including one for SqueezeNet. You can download the model and load it into CNTK:

import cntk as C
z = C.Function.load(<path of your ONNX model>, format=C.ModelFormat.ONNX)  

You can find tutorials for importing/exporting ONNX models in CNTK here.