We'll train an image classifier in Keras using a Tensorflow backend, then serve it to the browser using a super simple Flask backend. We can then deploy this flask app to google cloud using a few commands. Woot!
Code for this video:
https://github.com/llSourcell/how_to_deploy_a_keras_model_to_production
Please subscribe! And like. And comment. That's what keeps me going.
More learning resources:
https://blog.keras.io/keras-as-a-simplified-interface-to-tensorflow-tutorial.html#exporting-a-model-with-tensorflow-serving
http://machinelearningmastery.com/deploy-machine-learning-model-to-production/
https://news.ycombinator.com/item?id=13821217
https://www.quora.com/Should-keras-be-used-to-deploy-deep-learning-models-in-production
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
And please support me on Patreon:
https://www.patreon.com/user?u=3191693
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/
