Welcome to MLAPI’s documentation!

It is a simple API Framework for serving your Machine Learning model.

Don’t write glue code for API and Keras model! We did it for You!

Repository contents

API

• Flask API
• API Helper functions
• Images handling class
• API users management functions
• Image parsing methods

Models handling

• Models holder class
• Model controller class

Database and project management

• Manage
• DB connection config
• DB connection class
• DB models class

Indices

• Index
• Module Index
• Search Page

Getting started

We will show by example how to run Your own project.

Suppose our project is “Cats recognition” - does the picture contain a cat or not?

1. Save model

If you use Keras library, the first step is to save model as below:

# import necessary package
import h5py

# Define simple example Keras model
model = Sequential()
(...)
model.save('catsRecognition.h5')

After this process you will receive in the main project directory file: catsRecognition.h5.

2. Insert Your model into MLAPI

1. Go to mlapi main directory
2. /API/models/computed
3. Create Your own directory name for example “cats”
4. Insert your model file into folder /cats

3. Write config for Your model

[CATS]
modelName: cats
modelFullName: Cats Recognition
modelFile: catsRecognition.h5
outputValueType: class_probability
contentType: image

modelControllerClassOverrideFile: cats
modelControllerClassName: CatsClass

Save above lines in your /cats folder as config.ini

4. Write Class for Your model

• Model controller class

Check our ready models

• Car Recognition
• Polish Sentiment Analysis

TODO

Models which we plan to do. If you need model, just write to us office@ermlab.com or edit this document and create pull request :)

Contributors

Ermlab Software:

• Marcel Odya (@marcel-odya)
• Szymon Płotka (@simongeek)
• Krzysztof Sopyła (@ksopyla)