This repo contains finished code for the deployment project of Udacity's Machine Learning Engineer Nanodegree.
This is the workflow followed:
- Download or otherwise retrieve the data.
- Process / Prepare the data.
- Upload the processed data to S3.
- Train a chosen model.
- Test the trained model (typically using a batch transform job).
- Deploy the trained model.
- Use the deployed model.
The IMDB Reviews dataset can be downloaded as a .tar
file from this link.
On the far right is the model which is deployed using SageMaker. The model is a custom Pytorch LSTM model. On the far left is the web app that collects a user's movie review, sends it off and expects a positive or negative sentiment in return. In the middle lies a Lambda function, that can be executed whenever a specified event occurs. This function is given permission to send and recieve data from a SageMaker endpoint.