The objective of this project is to develop a model to detect and identify fashion objects in images and provide bounding box coordinates for each identified fashion class. This project utilizes an object detection model trained on fashion categories, specifically the YOLOv5 network from Ultralytics.
I have also created a blog post underlining the process, evaluation, analysis, recommendations, and sample results on this project, available here: https://www.joankusuma.com/post/object-detection-model-yolov5-on-fashion-images
The dataset used to train the model is available here:
@online{Eileen2020,
author = {Eileen Li, Eric Kim, Andrew Zhai, Josh Beal, Kunlong Gu},
title = {Bootstrapping Complete The Look at Pinterest},
year = {2020}
}