Doing a basic web deployment of a deep learning model is good way to prototype how your model will be used and to validate assumptions that you made during the training process. While working with Keras, I did simple deployments of several models and published articles describing my experience deploying Keras models with Facebook Messenger and Flask.

Since I have been spending a lot of time in the last year using the other major high-level deep learning framework, fastai, I wanted to get practical experience with simple deployments of fastai models. I decided to adapt the the approach I used for web deployment of Keras models with Flask. In this article I will describe some of the hurdles I had to overcome to create simple web deployments of fastai models, as well as some unexpected benefits that fastai provides for deployment compared to Keras.

#deep-learning #fastai #deployment #flask #keras