Connecting

[Alex Ellis]

Hi @Hvass-Labs,

I've forked your work and packaged it as a "Serverless" OpenFaaS function”. This effectively makes TensorFlow and ImageNet a web-service which takes a URL as input and gives categorisations back as a JSON response.

https://github.com/faas-and-furious/inception-function

I have several opportunities to demonstrate machine-learning with OpenFaaS at Dockercon EU (in two weeks) and KubeCon in December. I'd like to connect and talk more. If you're interested ping [e-mail] or link back-to the repository.

The code has also been packed with Docker which can make the tutorial more accessible on any platform.

[Hvass-Labs]

Thanks for making this!

I have added a new file with a list of selected forks which is linked from the main repo's README.md:

https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/forks.md

I have not tested your code. I don't know how and I am also pressed for time at the moment. But I did notice you included several files you probably don't need, if you are only using the Inception and VGG16 models.

It has been quite a while since I wrote this code, but I don't think the following are used in inception.py:

• knifey.py
• reinforcement_learning.py
• convert.py
• cifar10.py

You could also remove more files, but I think that would require for you to remove functions from inception.py as well.