Overview

This collection allows you to label images classes using predictions of pretrained Metric Learning model and Reference Database.

All you need to start is:

• .CSV catalog with image_url and item_id fields
• Agent with GPU

assign tags using NN predictions	add new items to Reference Database
review assigned tags	manual search in Reference Database

Launch

Map

This map illustrates how each application in the collection connected to each other

Applications

• CSV Products Catalog To Images Project

CSV Products Catalog to Images Project

app

Convert .CSV catalog to Images Project

• Serve Metric Learning

Serve Metric Learning

app

Google landmarks challenge models

• Embeddings Calculator

Embeddings Calculator

app

Calculate embeddings for images project

• AI Recommendations

AI Recommendations

app

Recommends matching items from the catalog

• Metric Learning Labeling Tool

Metric Learning Labeling Tool

app

Use metric learning models to classify images

Demo Data

• .CSV table to import example — the table that is used in the first step of launch
• Grocery store shelves - labeled and untagged images for test

Grocery store shelves

project

Labeled images of products on the shelve: snacks, chips, crisps

For Developers

You can use sources from from any application to create your own.

You can also refer to our documentation:

• How to create Superivsely APP
• Learn SDK Basics with IPython Notebooks
• Complete Python SDK

About us

You can think of Supervisely as an Operating System available via Web Browser to help you solve Computer Vision tasks. The idea is to unify all the relevant tools that may be needed to make the development process as smooth and fast as possible.

More concretely, Supervisely includes the following functionality:

• Data labeling for images, videos, 3D point cloud and volumetric medical images (dicom)
• Data visualization and quality control
• State-Of-The-Art Deep Learning models for segmentation, detection, classification and other tasks
• Interactive tools for model performance analysis
• Specialized Deep Learning models to speed up data labeling (aka AI-assisted labeling)
• Synthetic data generation tools
• Instruments to make it easier to collaborate for data scientists, data labelers, domain experts and software engineers

One challenge is to make it possible for everyone to train and apply SOTA Deep Learning models directly from the Web Browser. To address it, we introduce an open sourced Supervisely Agent. All you need to do is to execute a single command on your machine with the GPU that installs the Agent. After that, you keep working in the browser and all the GPU related computations will be performed on the connected machine(s).

• for technical support please leave issues, questions or suggestions in our repo. Our team will try to help.
• also we can chat in slack channel
• if you are interested in Supervisely Enterprise Edition (EE) please send us a request or email Yuri Borisov at sales@supervise.ly