Clothes recognition and retrieval on clothing retails.

1. tensorflow (2.0.0a0), GPU version can also be used
2. opencv (4.1.0.25)

pip install -r requirements.txt

1. Run main.py to produce final classification result
2. Run cloth_detection.py to produce images with clothes detection bounding boxes.

We trained a Yolo-v3 object detection on DeepFashion2 dataset, pre-trained model weights (tensorflow weights and darknet weights) can be download here.

For the classifier, we use a relatively small dataset consists of only 46 clothes of 2 classes (clothes with stripes and clothes without stripes), the dataset can be download here.