Rob Geada

I had the same issue, resolved by using the --shape flag to specify image size for the train command, ie: `fauxtograph train --kl_ratio 0.005 --shape 64 64 ./images ./models/modelname`

Copying discussions I've had on Slack: I think TrustyAI can provide a lot of the capabilities that the modelmesh-proxy is aiming to provide, which would provide the advantage of not...