Basic Image labeling tool
complete solution for image annotation
complete solution for image annotation
complete solution for image annotation with advanced features
Drag and drop images to Supervisely, supported formats: .jpg, .jpeg, jpe, .mpo, .bmp, .png, .tiff, .tif, .webp, .nrrd
For semantic and instance segmentation tasks
images and JSON annotations
Images with corresponding annotations
Clone project or dataset to selected workspace or project, works with all project types: images / videos / 3d / dicom
Transform project to YOLO v5 format and prepares tar archive for download
Transform YOLO v5 format to supervisely project
Converts Supervisely to COCO format and prepares tar archive for download
Export only labeled items and prepares downloadable tar archive
Import images from cloud (Google Cloud Storage, Amazon S3, Microsoft Azure, ...)
Use deployed neural network in labeling interface
Upload images using .CSV file
Dashboard to configure and monitor training
NN Inference on images in project or dataset
Import images with binary masks as annotations
Transform Supervisely format to YOLOv8 format
Converts Supervisely Project to Pascal VOC format
Converts COCO format to Supervisely
Dashboard to configure, start and monitor YOLOv8 training
Merge selected datasets with images or videos into a single one
Deploy model as REST API service
Download activity as csv file
Converts shapes of classes (e.g. polygon to bitmap) and all corresponding objects
Creates project with images grouped by selected metadata, converting DICOM data to NRRD format in the process.
State-of-the art object segmentation model in Labeling Interface
Creates images project from video project
Download images from project or dataset.
Assigns tags (train/val) to images. Training apps will use these tags to split data.
Detailed statistics for all classes in images project
Filters images and provides results in selected format
Dashboard to configure, start and monitor training
Read every n-th frame and save to images project
Import public or custom data in Pascal VOC format to Supervisely
Deploy model as REST API service
Merge multiple classes with same shape to a single one
Dashboard to configure, start and monitor training
Deploy YOLOv8 as REST API service
Connect your remote storage and import data without duplication. Data is stored on your server but visible in Supervisely
Dashboard to configure, start and monitor training
Use neural network in labeling interface to classify images and objects
Upload images by reading links (Google Cloud Storage) from CSV file
Prepare training data for SmartTool
Deploy ClickSEG models for interactive instance segmentation
Export images in DOTA format and prepares downloadable archive
Deploy model as REST API service
Dashboard to configure, start and monitor training
Copies images + annotations + images metadata
Use metric learning models to classify images
Converts Supervisely annotations to Cityscapes format and prepares downloadable tar archive
Dashboard to configure, start and monitor training
Generate synthetic data: flying foregrounds on top of backgrounds
Deploy model as REST API service
Visualize and build augmentation pipeline with ImgAug
Batched smart labeling tool for Images
Visual diff and merge tool helps compare images in two projects
Dashboard to configure, start and monitor training
Configure, preview and split images and annotations with sliding window
Visual diff and merge tool helps compare project tags and classes
Training dashboard for mmdetection framework (v3.0.0 and above).
Convert .CSV catalog to Images Project
label project images or objects using NN
Class-agnostic interactive detection for auto-prelabeling
Import Cityscapes to Supervisely
Converts Supervisely format to COCO Keypoints
Deploy model as REST API service
Image Pixel Classification using ilastik
for both images and their annotations
Split one or multiple datasets into parts
Detailed statistics and distribution of object sizes (width, height, area)
Interactive Confusion matrix, mAP, ROC and more
Creates new project with cropped objects
Deploy model as REST API service
Convert classes to bitmap and rasterize objects without intersections
Class-angnostic object detection model
Run HQ-SAM and then use in labeling tool
Download CSV file with download links for images
Review images annotations object by object with ease
Deploy model as REST API service
Deploy MMDetection 3.0 model as a REST API service
Explore images for every combination of classes pairs in co-occurrence table
Export Images Metadata from Project
Creates video project from images project
Split "AnyShape" classes to classes with strictly defined shapes (polygon, bitmap, ...)
Label project images using detector and pose estimator
Import images groups connected via user defined tag
Deploy model as REST API service
Label project images using detector and classify predicted boxes
Import Metadata for Images in Project
Explore images with certain number of objects of specific class
Assign tags to images using example images
Filter objects and tags by user and copy them to working area
Edit tags of each object on image
Interactive evaluation of your instance segmentation model
interactive metrics analysis
Calculate and visualize embeddings
Convert polygon and bitmap labels to semantic segmentation
Put images with labels into collage and renders comparison videos
SmartTool integration of Efficient Interactive Segmentation (EISeg)
to TorchScript and ONNX formats
Export items after the passing labeling job review
Downloads images from the Pexels to the dataset.
Evaluate your classification model
Converts annotations from Supervisely to COCO format as RLE masks with preserving holes
Filter and rank images by text prompts with CLIP models
Creates video from images in dataset with selected frame rate and configurable label opacity
Preview images as a grid gallery
Train HRDA model for segmentation in semi-supervised mode
Converts COCO Keypoints format to Supervisely
Rotates images along with the annotations in the dataset
Objects with specific tag will be treated as reference items
Google landmarks challenge models
Convert all labels in the project or dataset to rotated bounding boxes
Binds nested objects into groups
Build labels distribution heatmap for dataset.
Label project images using object segmentor
Merge multiple image projects into a single one
Add dataset name tag to all images in project or dataset
Merge images and labels that were split by sliding window before
Create foreground mask from alpha channel of image
Compare annotations of multiple labelers
Recommends matching items from the catalog
Generate synthetic data for classification of retail products on grocery shelves
Rename "Key:Value" tags to key_value (fruit: lemon -> fruit_lemon)
Export project to Google Cloud Storage, Amazon S3, Microsoft Azure, ...
Calculate embeddings for images project
Convert and copy multiple Roboflow projects into Supervisely at once.
Saves tag to images mapping to a json file
Text Detection and Recognition on images
Dashboard to configure, start and monitor YOLOv5 2.0 training
Explore images for every combination of tags pairs in co-occurrence table
App to obscure data on images and videos
Match image tag with CSV columns and add row values to image
Deploy HRDA model for inference
Drag and drop PDFs to import pages as images to Supervisely
Convert and copy multiple Labelbox projects into Supervisely at once.
Transfer and filter assets(images) between Supervisely instances
Import image projects in Supervisely format from cloud (Google Cloud Storage, Amazon S3, Microsoft Azure, ...)
No description available
Tags and object classes can be customized
Merge Tags in videos or images project
Import images and videos with annotations in CVAT format.
Import multispectral images as channels or as separate images.
Slice volumes to 2d images
Create a new empty project with a meta of original project
Create new object classes from tags associated with objects
Deploy model as REST API service
Run Stable Diffusion model with User Interface
This app perspective transforms and warps your images using qr code in them.
Deploy YOLOv5 2.0 as REST API service
Convert each class name to tag associated with objects, and merge existing classes into single one
Deploy InSPyReNet for salient object segmentation as a REST API service
Convert and copy multiple V7 datasets into Supervisely at once.
Downloads images from the Flickr to the dataset.
Application imports kaggle dataset 'Movie genre from its poster' as supervisely project
Apply pretrained models for underwater species detection
Evaluate your classification model in Detector + Classifier Pipeline
Import images and videos with annotations in V7 format.
Prepare examples for products from catalog
Convert and copy multiple CVAT projects into Supervisely at once.
Sample images from project with different methods
Supports multi-user mode
Deploy Transfiner for instance segmentation as a REST API service
Deploy SelfReformer for salient object segmentation as a REST API service
to TorchScript and ONNX formats
Review and correct tags (supports multi-user mode)
6 images with annotated lemons and kiwifruits
Image project with person instances
Sample images project without labels
Labeled images: snacks: chips / crisps / mix
Labeled roads (sample: 100 images, full version: 1000 images)
17 unlabeled images for quick tests
156 unlabeled images with roads
Tag (name of breed) is assigned to every image
Labeled images of products on the shelve: snacks, chips, crisps
10 images with labeled road
594 unlabeled images
Project with 66 annotated tomatoes (424 images)
726 sample gt-labeled images
Unlabeled images: sunflower / pumpkin (peeled + unpeeled) / mix
1171 sample gt-labeled images
Synthetic dataset for cracks segmentation
What breed is this cat? demo for visual tagging app
1171 sample prediction-labeled images
For object detection tutorials
Images of wheat for training and validation
726 sample pred-labeled images
For object detection tutorials
Wheat images for test
Illustrates alpha support in Supervisely