Food Waste CV

Food Waste CV

Finds food-waste categories on cafeteria trays in a photo using a small YOLO11n detector. An early prototype for exploring and triaging waste, not for accounting or compliance.

Made by archiii on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Food Waste CV is an early prototype, version 0.3, that spots food-waste categories on a cafeteria tray photo. A YOLO11n object detector looks for rice, veg, cooked meat, carbs, tissue and sauce. It is a Gradio demo meant for exploration.

Who it suits: It suits cafeteria managers, sustainability teams and students who want to see how computer vision could sort tray waste. It also suits developers who want a small detector wrapped in a Gradio page.

Industry | Who uses it | How they use it | Example
Food service | Cafeteria managers | Explore what ends up on returned trays | Upload a tray photo and read the labels
Sustainability | Waste-reduction teams | Triage waste categories before a full study | Check which categories the detector finds
Education | Computer vision students | Study a small YOLO detector | Read app.py and the weights file
Software | Developers | Wrap a custom detector in a web demo | Swap in their own weights

Anyone who needs automated accounting or compliance reporting can skip it, since the author says it is not meant for that.

Where to use it: The demo runs in two places.

• A web browser, on the page of the Space at Hugging Face
• Windows, macOS or Linux, as a local copy run with Python 3.11

Use case | Who | What they get back
Tray photo check | Cafeteria staff | Labels for waste categories found on the tray
Triage | Sustainability teams | A rough view of what kinds of food are left
Detector study | Students | A working example with trained weights

How to set it up: The online page needs nothing installed. A local copy needs the following.

• Python 3.11
• Windows, macOS or Linux
• The packages listed in requirements.txt

1. Install Python 3.11.
2. Install the Hugging Face hub package and download a copy of the Space.
3. Move into the new folder and install Gradio 5.25.0 and the packages in requirements.txt.
4. Start the app with python app.py.

pip install -U huggingface_hub
hf download archiii/food-waste-cv-demo --repo-type space --local-dir food-waste-cv-demo
cd food-waste-cv-demo
pip install gradio==5.25.0
pip install -r requirements.txt
python app.py

How to use it: Open the page, give it a photo of a cafeteria tray, and read the categories it marks. On a local copy, this command starts the page.

python app.py

Tool | What it does
YOLO11n detector | Finds food-waste categories in the photo
best.pt | The trained weights the app loads
app.py | Holds the Gradio page
requirements.txt | Lists the Python packages the app needs

Example: You upload a photo of a used tray with rice, a tissue and some sauce on it. The page marks the items it recognizes with their categories, though it may miss some.

For newcomers and experts: If you are new to this, treat the output as a first look. Check each marked item yourself, since the detector can miss things even when its labels are right.

If you know the field, this is a YOLO11n model trained at an image size of 960, with a validation mAP50 of about 0.43. The author says it works best on tissue and sauce, and plays it safe on the other classes. That means a label it gives is usually correct, but some items go undetected.

Photo of a tray
YOLO11n detects waste items
Categories are labeled
You review what it missed

Good to know: This is early work. The app itself carries caveats, and the author says to use it for exploring and triage only.

• License: AGPL-3.0, which comes from the Ultralytics YOLO11 code it builds on
• Cost to run: none named
• Data it reaches: the photos you give it and the weights file in the repository
• Not for: automated accounting or compliance use

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: agpl-3.0

Links

• Space: https://huggingface.co/spaces/archiii/food-waste-cv-demo
• Files: https://huggingface.co/spaces/archiii/food-waste-cv-demo/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.