MMFashion : A Machine Learning Model for Fashion Segmentation
This is an introduction to「MMFashion」, a machine learning model that can be used with ailia SDK. You can easily use this model to create AI applications using ailia SDK as well as many other ready-to-use ailia MODELS.
Overview
MMFashion is an open source toolbox for fashion analysis, which includes models for segmentation and landmark detection. In this article, we will introduce segmentation.

Source:https://arxiv.org/pdf/2005.08847.pdf
Fashion segmentation using MMFashion
MMFashion uses MMDetection as backend, and more specifically MaskRCNN included in MMDetection to perform segmentation on the input image.
At the time of writing it is able to detect the following categories.
CATEGORY = (
'top', 'skirt', 'leggings', 'dress', 'outer', 'pants', 'bag',
'neckwear', 'headwear', 'eyeglass', 'belt', 'footwear', 'hair',
'skin', 'face'
)

Source:https://github.com/open-mmlab/mmfashion/blob/master/demo/imgs/01_4_full.jpg
Export to ONNX
The procedure of exporting a model using MMDetection to ONNX is a bit complicated and it is described in the following article.
How to use MMFashion with ailia SDK
To use MMFashion with the ailia SDK, use the following command to perform segmentation on the input of the webcam.
python3 mmfashion.py -v 0
ailia Inc. has developed ailia SDK, which enables cross-platform, GPU-based rapid inference.
ailia Inc. provides a wide range of services from consulting and model creation, to the development of AI-based applications and SDKs. Feel free to contact us for any inquiry.
ailia Tech BLOG