This computer vision model detects logos and print on clothes pictures. It works with studio pictures as well as second hands picture.
It can be use to recognize brands or logo, to classify clothes or to detect plagiarism.
It has been trained on a dataset made up of 8k second hand (=amateur) pictures.
The base model is
yolov8n that has been retrained using Ultralytics toolset. You can see the training
parameters at
neural-network-transfer-learning.ipynb and
yolo_runs folder.
The dataset has been curated by hand. For any enquiry about the training
dataset,
contact me.
