
Roboflow simplifies the process of scaling datasets with its extensive library of pre-labeled data from Roboflow Universe, offers seamless integration with a variety of deployment options (including hosted API endpoints, private clouds, and edge devices), and provides an intuitive interface for fine-tuning and testing models. This makes Roboflow an excellent choice to enhance Supervisely-annotated datasets, and deploy models efficiently across diverse environments.
In this tutorial, you will learn how to import a Supervisely dataset into Roboflow, train a model, and deploy it.
Import Supervisely Datasets to Roboflow
Just follow these steps.
1. Find Datasets on Dataset Ninja
Head to Dataset Ninja and find a suitable dataset for your task. The example dataset used in this tutorial is the Supervisely Persons dataset, available here.
To use this dataset, click the "Train in Supervisely" button to annotate the images directly in Supervisely. Ensure your dataset includes annotations in a supported format like YOLOv8 for import into Roboflow.

Roboflow can be used to convert annotations between formats and supports 40+ different annotation formats.
2. Get the Data Out
Once annotated in Supervisely, download the dataset and export all images and annotations in the YOLOv8 format. This format is compatible with Roboflow and includes the necessary annotation files.

3. Import into Roboflow
Create a Roboflow account and log in. Click the "Create Project" button in the top right corner. Select "Instance Segmentation" as the project type, suitable for the Supervisely Persons dataset. Upload the YOLOv8 files from Supervisely to your project. The project example can be viewed here:
4. Train a Model in Roboflow
Configure the training parameters:
- Preprocessing: Auto-Orient (Applied), Resize (Stretch to 640x640)
- Augmentations: None
Train the dataset using a YOLOv11 (accurate) model. Monitor the training process in Roboflow to ensure the model learns effectively from the uploaded data.

5. Test the Model in Roboflow
Create a workflow in Roboflow and add a visualization block to view all detections. Test the workflow to evaluate the model's performance on the dataset, checking for accurate instance segmentation of persons.
6. Deploy the Model
Once testing is complete, roll out the trained model. Roboflow supports deployment to a cloud-based API endpoint, a private server, or edge hardware. Refer to Roboflow’s deployment instructions to configure the endpoint and incorporate it into your system.

Import Supervisely Datasets to Roboflow
By following this tutorial, you have learned how to import a Supervisely dataset into Roboflow, train a YOLOv11 model, test it, and deploy it for use. This process enables you to leverage annotated datasets for advanced computer vision tasks.
Written by Aarnav Shah
Cite this Post
Use the following entry to cite this post in your research:
Contributing Writer. (Aug 7, 2025). How to Import Supervisely Datasets to Roboflow. Roboflow Blog: https://blog.roboflow.com/import-supervisely-datasets/