Build with RF-DETR
Build a Product Detection App Free with RF-DETR
Find every product on a store shelf and get an instant count. Label shelf photos, train RF-DETR free, and deploy it as a workflow.
- No credit card
- No ML team required
- Edge, on-prem or API
Build a Product Detection App with Roboflow’s Free RF-DETR
In short
A product detection app uses computer vision to find every product in an image of a store shelf, display, or checkout, and count them. The model to train for it is RF-DETR, Roboflow's open-source real-time detection model, which handles dense shelves where products sit side by side. With Roboflow you label your shelf images, train RF-DETR for free, and deploy it as a workflow that returns an annotated image, a product count, and every detection.
How it works
The workflow behind the product detection app
Use this Product Detection with RF-DETR workflow: each shelf image goes to an RF-DETR model that finds every product, then through a confidence filter. The filtered products are counted on one track and boxed on the other, and both meet where the count is written onto the image. Every block is editable in the low-code builder, and the Roboflow Agent can build it from a description.
- output_image
- product_count
- predictions
How to build a product detection app with RF-DETR
Open the workflow and add your shelf photos
Click "Use this free template" to copy the workflow into your Roboflow workspace. Upload photos of your shelves taken from the angle and distance your phones or cameras will capture them.
Label products and train RF-DETR
Use Auto Label to draw a box around each product, then review and correct the results. Add classes for the SKUs or categories you need to tell apart. Train an RF-DETR model and select it in the detect_products block. RF-DETR fine-tunes well on small custom datasets, so you can start with the photos you have.
Tune the confidence threshold
Raise or lower the threshold in filter_by_confidence until the workflow counts every product without picking up price tags, labels, or shelf edges.
Deploy and connect it to your stores
Deploy the workflow as a Serverless Cloud API, or on your own hardware through Inference. Each image returns output_image, product_count, and predictions for your inventory system or dashboard to use.
Roboflow MCP
Build it from your AI assistant with the Roboflow MCP
Connect the Roboflow MCP Server to Claude, Cursor, or any MCP-compatible assistant and build the whole product detection app in natural language, without leaving your editor.
Ask an assistant like Codex or ChatGPT to search Roboflow Universe for retail product datasets, upload and auto-label your shelf photos, and train an RF-DETR model on your products. It can then create and run the product detection workflow on test images and deploy it to your devices.
Paste it into your coding agent and it walks you through the rest. Setting up by hand? The server is https://mcp.roboflow.com/mcp.
Open the Roboflow listing, select Connect, then sign in to Roboflow. Available on desktop, web and mobile.
Run these commands in your terminal, then sign in to Roboflow. Claude Code CLI has no documented browser install link.
Opens the Roboflow plugin listing. Sign in if prompted and confirm the install on Cursor to add MCP and skills.
Opens the Roboflow plugin listing. Install the plugin and sign in to Roboflow when prompted to connect your account.
Opens the Roboflow plugin listing shared by ChatGPT and Codex. Install the plugin and sign in to Roboflow when prompted to connect your account.
Then run /mcp auth roboflow in Gemini CLI to sign in. Gemini CLI has no documented browser install link.
What your product detection app can do
Trained on your shelf images, an RF-DETR model handles the specific, hard-to-catch cases that matter in your store:
- Separate products packed tightly side by side on a shelf
- Find small items like cans, jars, and boxes on crowded displays
- Detect products at an angle, partly hidden, or pushed to the back
- Keep detecting through glare from shelf lighting and glossy packaging
- Tell products apart from price tags, labels, and shelf edges
- Count every product on a shelf from one photo
Want to customize your product detection app?
Describe the product detection app you want in plain English: the store, the shelves, and the products you need to find. The Roboflow Agent finds the data, trains an RF-DETR model, and assembles the workflow for you.
Open source
Roboflow’s RF-DETR is open source, Apache-2.0, and free to use
RF-DETR is an open-source, Apache-2.0 licensed real-time object detection model developed by Roboflow. The rfdetr Python package and most RF-DETR models are free to use, including in commercial products, and you can train and run everything on your own hardware. No account or lock-in required.
Apache-2.0 and free
The rfdetr package, Nano to Large detection, every segmentation size and Keypoint are Apache-2.0 licensed and free to use, including commercially.
Install and train locally
pip install rfdetr on Python 3.10+. Fine-tune on your own data in a few lines and run it entirely on your machine.
State of the art on COCO
RF-DETR is a real-time detector that is SOTA on COCO. RF-DETR-Large reaches 56.5 AP at 6.8 ms on an NVIDIA T4, and uses a DINOv2 backbone.
Deploy anywhere
Export to ONNX or TensorRT and run on GPU, CPU, or NVIDIA Jetson at the edge, or serve it through the Roboflow hosted API.
| Models | Licence |
|---|---|
| Detection: Nano, Small, Medium, Large | Apache-2.0 |
| Segmentation: every size, Nano to 2XLarge | Apache-2.0 |
| Keypoint (preview) | Apache-2.0 |
| Detection: Atto, Femto, Pico, XL, 2XL (rfdetr[plus]) | PML 1.0: commercial use included on Roboflow; commercial self-hosting needs the Enterprise add-on |
RF-DETR vs. other free detectors
A product detection app has to find dozens of small, tightly packed products in a single shelf image, so the model needs to be both accurate and fast. Here is how RF-DETR, fine-tuned on your own shelf photos, compares for retail detection.
| Model | Tasks | Best for | License |
|---|---|---|---|
| RF-DETR | Detection, segmentation (keypoints in preview) | Real-time detection you fine-tune on your own data, one model across tasks | Apache-2.0 (Nano to Large, all segmentation); PML 1.0 (Atto, Femto, Pico, XL, 2XL) |
| D-FINE | Detection | Precision localization when you do not need to fine-tune | Apache-2.0 |
| YOLO | Detection, segmentation, pose | Fast CNN-based detection with a large ecosystem | AGPL-3.0 (commercial license required for closed-source use) |
| GroundingDINO | Open-vocabulary detection | Finding objects by text prompt with no training, not real-time | Apache-2.0 |
| SAM 2 / SAM 3 | Segmentation | Pixel-precise masks; SAM 3 adds text-prompted segmentation | Apache-2.0 (SAM 2), SAM License (SAM 3) |
| Florence-2 | Vision-language | Reading, captioning, and OCR on images | MIT |
The takeaway for this app: RF-DETR runs in real time, so it can process shelf photos and camera feeds across many stores. It fine-tunes well on small custom datasets and is open source, so you can train on your own products and run the model wherever your cameras are.
Build your product detection app free today
Label, train, and deploy your product detection app in one place.