Fine-tuning a pre-trained model in TensorFlow and use of NCS

[idata]

I am interested to know if anyone has tried finetuning a pre-trained model in TensorFlow and used them in an NCS?

I am trying the above for a VGG16 model. But there are unsupported operations that are preventing me from doing this. Here's the notebook where one can see how I am creating the model and necessary files for generating the NCS graph. Help would be appreciated. I am using v2 of NCSDK, btw.

Thanks.

[idata]

@Tome_at_Intel would you be able to lament on this? That would be of much help.

[idata]

@Sayak_Paul

Hi Sayak,

It is possible to run a custom VGG16 Model on the NCS. What error messages were you getting (What were the unsupported operations)?

Best Regards,

Aroop