Train, serve & apply

Ultimate ecosystem for neural networks

The only platform that unifies the best models, ML tools for analysis and model improvement and numerous applications built on top.

Train

Build models from labeled data using the best architectures

Serve

Deploy trained models as API on cluster and use in other Apps

Apply

Use served models in infinite various applications

From GitHub

New models are easy to integrate by forking and wrapping

Custom models

Integrate your model to benefit from Apps in Ecosystem

More of ecosystem 🔥

Explore our growing collections of machine learning tools

Custom applications

Create custom labeling UIs tailored for your task

Trusted by Fortune 500. Used by 80,000+ companies and researchers worldwide

For every step in AI pipeline

From Zero to Hero and beyond

Because Supervisely is built like OS for computer vision, we made possible integration of the best machine learning models and tools on a single platform.

You will find a well-known projects from data science community, as well as our own Apps, providing a complete solution for entire AI development pipeline.

Train state-of-the-art models in browser

Learn more

Configure every aspect of training from target classes to online augmentations, monitor metrics and terminal logs in real-time.

Noticeable example app:

Visualize, analyze and improve performance

Learn more

Understand how your model works on ground truth and new data and find how to correct negative output and increase performance.

Noticeable example app:

Apply models in various scenarios and interfaces

Learn more

Put pre-trained or custom neural network models to use in labeling interfaces to archive extraordinary results.

Noticeable example app:

Boost training with synthetic data

Learn more

Generate synthetic datasets that drastically improve model results, especially when there is not enough ground truth.

Noticeable example app:

Query and transform, run augmentations

Learn more

Perform all the necessary actions on your data, from importing and converting to skeletonization of masks and rasterization.

Noticeable example app:

Integrations

From GitHub to Supervisely Apps — why?

You noticed we have some of the best models and machine learning tools integrated to Supervisely and maybe thinking right now: why is better to use them as Supervisely Apps instead of cloning a GitHub repo and setting things up yourself?

More about Apps
  • Start in a single click

    Don't waste dozen of hours figuring out how to install, configure and adapt another model from the internet — we did the hard part for you.

  • Convenient UI

    Thanks to streamlined way of building interfaces with Supervisely Apps, we can add GUI simplify interaction with integrated code.

  • Deploy on any machine

    Run automatically generated command in terminal to run Supervisely Agent and simply deploy new training tasks with a few clicks.

5

reasonswhy
  • Team collaboration

    Since now those models and tools run in web and not on your personal PC, you can easily share and collaborate with your team members.

  • Integration with other Apps

    Project converted to App gets access to the whole Ecosystem: import from different formats, visualization, exploration and much more!


Already there

Just some of the integrated models

Feel to free explore Supervisely Ecosystem and find more integrated projects and, on top of that, much more custom built solutions by Community and Supervisely Team.

Explore Ecosystem

Classification

MMClassification

Semantic Segmentation

MMSegmentation UNet

Interactive Segmentation

EISeg RITM

Object Tracking

FairMOT

3D Object Tracking

MMDet3D Open3D-ML

MMClassification

open-mmlab/mmclassification

MMClassification is an open source image classification toolbox based on PyTorch. It is a part of the OpenMMLab project.

MMSegmentation

open-mmlab/mmsegmentation

MMSegmentation is an open source semantic segmentation toolbox based on PyTorch. It is a part of the OpenMMLab project.

UNet

zhixuhao/unet

PyTorch implementation of the U-Net for image semantic segmentation with high quality images.

MMDetection

open-mmlab/mmdetection

OpenMMLab Detection Toolbox and Benchmark.

YOLOv5

ultralytics/yolov5

YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset.

Detectron2

facebookresearch/detectron2

Detectron2 provides us Mask R-CNN Instance Segmentation baselines based on 3 different backbone combinations.

EISeg

PaddlePaddle/PaddleSeg

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks.

RITM

saic-vul/ritm_interactive_segmentation

State-of-the art click-based interactive segmentation integrated into Supervisely Image Annotator.

FairMOT

ifzhang/FairMOT

State-of-the art Multiple Object Tracking.

MMDetection3D

open-mmlab/mmdetection3d

OpenMMLab's next-generation platform for general 3D object detection.

Coming soon

Open3D ML

isl-org/Open3D-ML

An extension of Open3D to address 3D Machine Learning tasks.

Coming soon

Deploy

Create computational cluster with a single command

Connect your machines (servers or PCs) to Supervisely by running automatically generated command in the terminal. It starts Supervisely Agent — a tiny program that let's you run Supervisely Apps.

Start training neural networks, serve models, run various machine learning tools and other Apps from our Ecosystem right from the web interface.

We handle all the boring configuration, monitoring and log collection routine for you — simple focus on what you like!

1.

Copy

generated command
bash <(curl -s "https://app.supervisely.com/api/agent/tkqvwSTC0ca5")

2.

Paste

on your machine
me@PC:/work$ bash <(curl -s "https://app.supervisely.com/api/agent/tkqvwSTC0ca5")

3.

Deploy

tasks in one click

Train

The most advanced training dashboard in your browser

Most of our integrated models are trainable and each corresponding Supervisely App comes all the necessary functionality for effective model training.

You can configure every aspect of training from target classes to online augmentations, monitor metrics, visualizations and terminal logs in real-time.

Training 1 / 3

Data preparation

Automatic train & val splits
Select classes & see stats
Online augmentations
Automatic data validation

Training supports multiple strategies for train / validation splits: random split with defined percentage, based on image tags or datasets.

Training 2 / 3

Model training

Choose pre-trained or custom weights
Configure any hyper-parameter
Monitor real-time charts, logs & visualizations
Checkpoints & artifacts in a structured way

Choose model architecture or how weight should be initialized.

Training 3 / 3

Infrastructure & collaboration

Easy to run on any computer with GPU
Multiple experiments in parallel have never been so easy
Easy collaboration
  • You can connect any GPU computer using Supervisely Agent: just run a single command in the terminal and your machine will be ready to get tasks from the platform even if you are in a private network or don’t have static IP address.
  • All neural networks support Supervisely Annotation Format out of the box. Run training from the project context menu in a few clicks.
  • Agent receives a task, automatically downloads labeled project and spawns training dashboard on the computer you chose.

Serve

Deploy model once. Use it everywhere.

Run a pre-trained model or your custom trained weights and deploy it on any machine, connected via Supervisely Agent.

Original GitHub repo

Carefully selected machine learning toolboxes with open licenses and state-of-the-art models

Supervisely App

Create and publish a new GitHub repo to Ecosystem by adding a simple bootstrap code

ECOSYSTEM

Docker Container

Create and publish a new GitHub repo to Ecosystem by adding a simple bootstrap code

API

Apply

Make the most of deployed AI models

Explore ecosystem of ready-to-use Supervisely Apps that work on top of deployed neural networks and supercharge various aspects of labeling with AI.

SUPERVISELY FOR ENTERPRISES

On-premise edition built for your business

A fully customizable AI infrastructure, deployed on cloud or your servers with everything you love about Supervisely, plus advanced security, control, and support.

Start 30 days free trial
  • Maximum security: hosted behind firewall on your servers with advanced governance and privacy settings
  • Effortless integrations: single sign-on with LDAP or OpenID, cloud storage in AWS or Azure and powerful API & SDK
  • Priority support: dedicated slack chat, guided onboarding and personalized training sessions with experts
supervisely install
> downloading pre-requirements...
> pulling docker images...
> installing software...
> Done! Supervisely is running on port :80

supervisely update
> checking for updates...
> Your version is up to date!
Supervisely slack logo
#support
Team Manager 17:33
Hello @supervisely! Is there a way to create a project via API?
Supervisely 17:35
Sure thing, check out this docs!

Here’s why our customers trust us

Engie customer testimonial
Quote mark

We use Supervisely since 2019. The key advantage of this tool is that Supervisely provides a complete data treatment pipeline. An important advantage is that a Supervisely instance can be deployed autonomously on a Client infrastructure, and distributed on different servers.

It helps to treat enterprise’s internal and often confidential data in a secured way. Together with a user-friendly interface, a clear documentation and a friendly and reactive support team it helps us to do Data Scientist work better and faster.

engie-logo
Dmitriy Slutskiy
PhD Research Engineer
BMW customer testimonial

BMW Group is using the Supervise.ly solution to create automated verifications for ensuring a very high product quality across the whole production chain in vehicle and vehicle component manufacturing.

BMW Group uses Supervise.ly to annotate manufacturing images from production lines in their world-wide plants for enhancing quality inspections using deep learning. The Supervise.ly tooling also supports the process for continuously updating AI models using semi-automated labeling.

Supervise.ly is integrated into the BMW Group AI Platform in order to empower computer vision based AI use cases.

Surgar customer testimonial
Quote mark

We’ve been working together with Supervisely since 2020, and we have helped each other to grow rapidly and significantly.

Supervisely’s team has been incredibly fast and agile in taking on board our requirements and implementing useful, up-to-date computer vision functionalities. In addition, we appreciate the openness and scalability of their ecosystem combined with the Python SDK and API. So far, we have been very satisfied with the platform and the incredibly responsive team.

surgar-logo
Julien Peyras
Director of Data Science Department
UCD customer testimonial
Quote mark

Working with Supervise.ly has significantly enhanced our capability to develop AI models for lung CT scans. What sets Supervise.ly apart is its exceptional support team who are really responsive and adapt to our unique needs with a range of apps and helper files.

Their team has developed updates driven by our specific user feedback, making Supervise.ly a critical component of our research ecosystem in generating the specific labels we need to provide AI-driven solutions. We are immensely grateful for their pivotal role in our work.

ucd-logo
Katie Noonan
AI Research Engineer
Resson customer testimonial
Quote mark

We originally set out to look for tools that could help us with data annotation, and we discovered that Supervisely excels at that and much more. It has become an integral part of our workflow in annotation, model training, and evaluation.

We've been exceedingly impressed with the customer support, addition of new features, and the flexibility of the publicly available SDK/API. The Supervisely team has also been fast to respond to support questions, and has shown a lot of openness when given feedback on potential improvements.

resson-logo
Travis Prosser
Engineering Specialist
Toadi customer testimonial
Quote mark

We have been using Supervisely for a few years now to help label and organize our data for AI training. The interface is user-friendly and the tools are intuitive to use, which has made the annotation process much more efficient for our team. We run Supervisely locally, which allows us to stay in control of our data. We also use Supervisely for annotation reviews, and the review tools have been invaluable in ensuring the quality and accuracy. The Python SDK has also been incredibly helpful in automating and streamlining our workflow. In addition, the support team on Slack has been extremely helpful and responsive. The ability to collaborate with my colleagues on the same project has also been a huge time-saver.

Overall, we have been extremely satisfied with Supervisely and would highly recommend it to anyone in need of a reliable and efficient annotation solution.

eeve-logo
Mike Slembrouck
CTO

7

years

Supervisely provides first-rate experience since 2017, longer than most of computer vision platforms over there.

80,000+

users

Join community of thousands computer vision enthusiasts and companies of every size that use Supervisely every day.

1,000,000,000+

labels

Our online version has over a 220 million of images and over a billion of labels created by our great community.

Trusted by Fortune 500. Used by 80,000+ companies and researchers worldwide

Contact Us

Ready to get started?

Speak with people who are on the same page with you. An actual data scientist will:

  • Show live demo
  • Go through the concepts
  • Learn your case
  • Offer a tailored solution

Get you data labeled

Get accurate training data on scale with expert annotators, ML-assisted tools, dedicated project manager and the leading labeling platform.

Order workforce