Retail Coolers Computer Vision Project

Drop an image or

This project was created after collecting images from retail coolers at Walgreens stores in Chicago, Illinois and Iowa City, Iowa.

All products are marked/labeled as product, and all empty spaces are labeled as empty

This is a good starter-dataset for anyone interested in doing "void space" calculations (percent of space that is empty), product inventory counts, or making more custom classes for individual product inventory counts.

Versions 2 and 3 were trained from the Microsoft COCO model checkpoint.

Versions 4 and 5 were trained from the SKU-110k model's training checkpoint, from the Roboflow Universe Retail datasets page.

For more, check out the blog posts below:

  1. https://blog.roboflow.com/using-computer-vision-to-keep-stock-of-inventory/
  2. https://blog.roboflow.com/retail-store-item-detection-using-yolov5/

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.


This project has a YOLOv8 model checkpoint available for inference with Roboflow Deploy. YOLOv8 is a new state-of-the-art real-time object detection model.

Cite this Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{ retail-coolers_dataset,
    title = { Retail Coolers Dataset },
    type = { Open Source Dataset },
    author = { Roboflow Universe Projects },
    howpublished = { \url{ https://universe.roboflow.com/roboflow-universe-projects/retail-coolers } },
    url = { https://universe.roboflow.com/roboflow-universe-projects/retail-coolers },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2023 },
    month = { jan },
    note = { visited on 2023-01-28 },

Last Updated

17 days ago

Project Type

Object Detection




empty, product


CC BY 4.0