Deployment

Main

Organization

Project

Private HUB

Ikomia HUB

Organization search

Project search

Workflow

Add members

Algorithms are the building blocks of your Computer Vision workflows. You can create and share your own algorithms or use the ones provided by the community on Ikomia HUB.

You have no algorithm yet.

There is no algorithm in this workspace (or you don't have access to any).

<bold>{{count}} credit</bold> will expire on <bold>{{date}}</bold> if you don't use it before.

<bold>{{count}} credits</bold> will expire on <bold>{{date}}</bold> if you don't use them before.

Credits expiring soon

Deployments may not be available until your balance is positive.

You have no credits left

Balance

The amount of credits you have left currently. Next credits to expire will be used first.

Balance summary

To get credits and be able to deploy workflows in this workspace, you need to subscribe to a plan.

This workspace has no current plan

You can edit your subscription plan at any time. Your new plan will be effective immediately after payment.

Change your plan

Organization name

Create an organization

Project name

Create a new project

Please copy it and keep it in a safe place. You won't be able to see it again.

Your token has been generated

Name

Create a new token

Are you sure you want to delete this deployment? This action is irreversible.

Delete deployment "{{name}}"?

Are you sure you want to remove this member? You can add it again later.

Remove member {{name}}?

Are you sure you want to delete this organization? This action is irreversible.

Delete organization {{name}}?

Are you sure you want to delete this project? This action is irreversible.

Delete project "{{name}}"?

Are you sure you want to delete this token? You will be logged out of the application using this token.

Delete token "{{name}}"?

Are you sure you want to delete this workflow? This action is irreversible.

Delete workflow "{{name}}"?

Machine specifications

Conditions

Custom license

Limitations

Permissions

Package

Projects lets you organize multiple Computer Vision workflows.

You have no project yet.

There is no project in this workspace (or you don't have access to any).

License

Version

Publish algorithm

Time range selection

404 Not Found · Ikomia SCALE

404: Page Not Found

Members

Overview

Dashboard · Ikomia SCALE

Deployment {{name}} · Ikomia SCALE

Logs

Your role on project <project>{{projectName}}</project> limits your access to some feature of this deployment.

You have a limited access to this deployment

This action is irreversible. Applications will be disconnected.

Delete deployment

Take irreversible actions on your deployment.

Danger zone

Deployment settings · Ikomia SCALE

You can resize of your deployment to increase or decrease the resources allocated to it.
This will affect your deployment's performance.

Size

Deployment settings

It seems that the deployment is not available. Please check that the deployment is running and that the URL is correct.

Failed to connect to the deployment

{{name}} · Ikomia SCALE

Swagger

Demo

Filters

Deployments · Ikomia SCALE

Your deployments

Filter

Next-generation Computer Vision algorithms, for your eyes only.

Ready to use and editable Computer Vision algorithms from your favorite frameworks.

Organization workspace

Settings · {{name}} · Ikomia SCALE

Billing

Organization settings

You'll also appear in the organization's members list, which is visible to other members of the organization.

Only you can see this list

You can create one or be invited by someone else.

You are not in an organization.

Organizations

{{username}} · Ikomia SCALE

Your personal workspace

The basic information about your project.

About

Warning, this action is irreversible. All the data associated with this project will be deleted.

Delete project

Take irreversible actions on your project.

Project settings

Projects · Ikomia SCALE

Your projects

Sign in · Ikomia SCALE

Sign in to Ikomia

Sign up · Ikomia SCALE

Already have an account?

Create an Ikomia account

Just a few additional details and your account will be ready.

You can always disable this setting later.

Opt in to receive tips and updates.

Join Ikomia newsletter

Your username is public and cannot be changed.

Username

Onboarding · Ikomia SCALE

Almost there!

Enter your email and we'll send you a link to reset your password.

Forgot Password · Ikomia SCALE

The email contains a link that will allow you to reset your password.

We have sent you a recovery email!

Forgot password

Reset Password · Ikomia SCALE

Reset your Ikomia password

Ikomia API is an open-source API to train, test, and build reusable Computer Vision workflows. You can select and chain the best state-of-the-art algorithms from your preferred frameworks such as OpenCV, Detectron2, OpenMMLab or YOLO.

Reusable Computer Vision workflows in a few lines of code.

Ikomia API

Ikomia CLI is a command line interface to manage and deploy your Computer Vision project. It allows you to create, build and run workflows right from the command line.

Manage and deploy your Computer Vision project from the command line.

Ikomia CLI

Tools · Ikomia Docs

Ikomia STUDIO is a simple drag-and-drop User Interface to prototype Computer Vision solutions. With its double window, you can watch the effects of your treatments in seconds.

Using the command line

Or download Linux Installer

Desktop prototyping app for Computer Vision.

Ikomia STUDIO

Download Windows Installer

Install Ikomia tools and start building Computer Vision solutions in a more scalable manner.

Ikomia tools

Enter your token received by email to validate your account.

Account Validation · Ikomia SCALE

You now have access to all the features of our application.

Email address has been confirmed!

Account validation

Don't forget to check out our quick start guide to quickly get acquainted with our application and start enjoying its benefits.

If you have any questions, concerns, or need assistance, please do not hesitate to contact us at support@ikomia.ai. Our team is here to assist you every step of the way.

Thank you for being a part of Ikomia SCALE! We are excited to accompany you on your journey and help you achieve your goals.
Best regards,

The Ikomia SCALE Team

Your plan doesn't allow you to deploy workflows. Please upgrade to access this feature.

Deployments are not available in this workspace

Only project's managers and owners can add deployments.

You are not allowed to add deployments

Add a deployment to run your workflow on Ikomia SCALE infrastructure.

You don't have a deployment for this workflow

Deployments

The basic information about your workflow.

Delete workflow

Take irreversible actions on your workflow.

Workflow settings

<div align="center">
  <img src="https://raw.githubusercontent.com/Ikomia-hub/infer_sparseinst/main/icons/sparseinst.png" alt="Algorithm icon">
  <h1 align="center">infer_sparseinst</h1>
</div>
<br />
<p align="center">
    <a href="https://github.com/Ikomia-hub/infer_sparseinst">
        <img alt="Stars" src="https://img.shields.io/github/stars/Ikomia-hub/infer_sparseinst">
    </a>
    <a href="https://app.ikomia.ai/hub/">
        <img alt="Website" src="https://img.shields.io/website/http/app.ikomia.ai/en.svg?down_color=red&down_message=offline&up_message=online">
    </a>
    <a href="https://github.com/Ikomia-hub/infer_sparseinst/blob/main/LICENSE.md">
        <img alt="GitHub" src="https://img.shields.io/github/license/Ikomia-hub/infer_sparseinst.svg?color=blue">
    </a>    
    <br>
    <a href="https://discord.com/invite/82Tnw9UGGc">
        <img alt="Discord community" src="https://img.shields.io/badge/Discord-white?style=social&logo=discord">
    </a> 
</p>


Run Sparseinst instance segmentation models.

![Cat instance segmentation](https://raw.githubusercontent.com/Ikomia-hub/infer_sparseinst/main/icons/output.jpg)

## :rocket: Use with Ikomia API

#### 1. Install Ikomia API

We strongly recommend using a virtual environment. If you're not sure where to start, we offer a tutorial [here](https://www.ikomia.ai/blog/a-step-by-step-guide-to-creating-virtual-environments-in-python).

```sh
pip install ikomia
```

#### 2. Create your workflow


```python
from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_sparseinst", auto_connect=True)

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_cat.jpg")

# Inpect your result
display(algo.get_image_with_mask_and_graphics())
```

## :sunny: Use with Ikomia Studio

Ikomia Studio offers a friendly UI with the same features as the API.

- If you haven't started using Ikomia Studio yet, download and install it from [this page](https://www.ikomia.ai/studio).

- For additional guidance on getting started with Ikomia Studio, check out [this blog post](https://www.ikomia.ai/blog/how-to-get-started-with-ikomia-studio).

## :pencil: Set algorithm parameters

- **model_name** (str) - default 'sparse_inst_r50_giam_aug': Name of the Sparseinst model. Additional models are available:
    - sparse_inst_r50vd_base
    - sparse_inst_r50_giam
    - sparse_inst_r50_giam_soft
    - sparse_inst_r50_giam_aug
    - sparse_inst_r50_dcn_giam_aug
    - sparse_inst_r50vd_giam_aug
    - sparse_inst_r50vd_dcn_giam_aug
    - sparse_inst_r101_giam
    - sparse_inst_r101_dcn_giam
    - sparse_inst_pvt_b1_giam
    - sparse_inst_pvt_b2_li_giam

- **conf_thres** (float) default '0.5': Confidence threshold for the prediction [0,1]
- **config_file** (str, *optional*): Path to the .yaml config file.
- **model_weight_file** (str, *optional*): Path to model weights file .pth. 


```python
from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_sparseinst", auto_connect=True)

algo.set_parameters({
    "model_name": "sparse_inst_r50_giam",
    "conf_thres": "0.5",
})

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_cat.jpg")

# Inpect your result
display(algo.get_image_with_mask_and_graphics())
```

## :mag: Explore algorithm outputs

Every algorithm produces specific outputs, yet they can be explored them the same way using the Ikomia API. For a more in-depth understanding of managing algorithm outputs, please refer to the [documentation](https://ikomia-dev.github.io/python-api-documentation/advanced_guide/IO_management.html).

```python
import ikomia
from ikomia.dataprocess.workflow import Workflow

# Init your workflow
wf = Workflow()

# Add algorithm
algo = wf.add_task(name="infer_sparseinst", auto_connect=True)

# Run on your image  
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_cat.jpg")

# Iterate over outputs
for output in algo.get_outputs():
    # Print information
    print(output)
    # Export it to JSON
    output.to_json()
```

infer_sparseinst

Sparse Instance Activation for Real-Time Instance Segmentation

Infer Sparseinst instance segmentation models

Permissions	Conditions	Limitations
Commercial use	License and copyright notice	Liability
Modification		Warranty
Distribution
Private use

infer_sparseinst

About

🚀 Use with Ikomia API

1. Install Ikomia API

2. Create your workflow

☀️ Use with Ikomia Studio

📝 Set algorithm parameters

🔍 Explore algorithm outputs

Developer

Ikomia

License

MIT License