ailia Tech BLOG
ClothingDetection : A machine learning model for detecting clothing
This is an introduction to「ClothingDetection」, 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
Clothing Detection is a clothing recognition model that uses YOLOv3. It can detect the position of tops and bottoms from an input image.
Source：https://github.com/simaiden/Clothing-Detection/blob/master/tests/0000003.jpg
simaiden/Clothing-DetectionAll weights and config files are in…github.com
Recognized categories
ClothingDetection uses Modanet and DeepFashionV2 as datasets, it can detect and calculate bounding boxes for the following categories.
DATASETS_CATEGORY = {
‘modanet’: [
“bag”, “belt”, “boots”, “footwear”, “outer”, “dress”, “sunglasses”,
“pants”, “top”, “shorts”, “skirt”, “headwear”, “scarf/tie”
],
‘df2’: [
“short sleeve top”, “long sleeve top”, “short sleeve outwear”, “long sleeve outwear”,
“vest”, “sling”, “shorts”, “trousers”, “skirt”, “short sleeve dress”,
“long sleeve dress”, “vest dress”, “sling dress”
]
}
ModaNet is a data set for fashion segmentation provided by eBay, which includes 13 fashion categories.
Source：https://github.com/eBay/modanet
DeepFashionV2 is a large dataset for fashion detection, containing 491K images and 13 popular categories, for a total of 801K fashion items.
Source：https://github.com/switchablenorms/DeepFashion2
Usage
You can run Clothing Detection on the webcam video stream in ailia SDK with the following command.
python3 clothing-detection.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.