Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Get optimal results with your brand-new trained application by learning how to carry out actual image analyses with it.

...

Table of Contents
minLevel1
maxLevel7
excludeWhat to expect from this page?

📑 Get started

  1. Go tothe “IKOSA AI Dashboard”.

  2. Click on the “Training Overview” item or

  3. Scroll down Go to the “Latest Training Sessions” list.

...

Initially, your custom application will be in an undeployed mode with the status “successful“successful”.

Info

Please note: In the trial subscription plan you cannot train or deploy any application, as you don’t have access to IKOSA AI. To be able to train applications you have to contact us and purchase an IKOSA AI license. Per IKOSA AI license a single model can be trained. If you want to train another models, you have to request for an additional IKOSA AI Inference. Per each IKOSA AI Inference requested a single model can be trained.

For subsequently applying your custom application to new image data:

  1. Choose Deploy” from the hamburger button.

  2. When the status “deployed” is displayed, the status indicator switches from green to blue, and your application is ready for use.

...

Info

Please note: In order to Depending on your software package, you will be able to deploy another trained application, you have to first underlay the one currently displayed. To do this, choose Undeploy train and activate (deploy) a certain number of apps. If you need to deploy an app but the the maximum number if already activated, Undeploy one of the appsfrom the hamburger Button and proceed deploying the new app as shown above.

...

  1. Go to the “Training Overview” page.

  2. Click the “View your application” link.

  3. A window with images for analysis opens.

...

Step 2 - Select images and start the analysis

From the “Image Library” page

...

From the “Image Viewer”

Please note: It is best to use images that were not part of the training/validation set.

  1. In your “Image Library” choose a representative image (or multiple images) that you would like to have analyzed with your trained application.

  2. Click the “Image Analysis” button after selecting the image(s).

  3. Go

...

  1. to the “IKOSA AI Applications” tab.

  2. Choose your trained application.

  3. Start the analysis by clickingthe “Start job” button.

starting-analysis-from-image-library.mp4

...

Start image analysis directly from the “Image Viewer”.

  1. While in image viewing mode click the “Image Analysis” button.

  2. Go to the “IKOSA AI Applications” tab.

  3. Choose your trained application.

  4. Start the analysis by clicking the “Start job” button.

start-analysis-from-viewer.mp4

?? Collect your results

Step 1 -

...

Navigate to

...

the

...

You will then be redirected to the “Image Analysis” page.

...

Analysis Jobs

Once your analysis job is done, it will be displayed in the Finished tab.

  • Depending on the complexity of your trained model, the analysis might take a few moments in which the job will be in an Active state.

  • If your analysis job is not finished yet, you can refresh the analysis jobs results section anytime by clicking the “Refresh” (blue star) button.

...

  • .

...

Step

...

2 - Download your results

...

  • Get only an individual output file fora single image by opening the drop-down menu next to it and downloading the desired file.

...

  • Get all result outputs fora single image by clicking the “Download” icon next to it.

  • Get a zipped file containing the result outputs for all images in the project by clicking the “Download all” button above the table.

    download all.mp4

  • Get a zipped file containing the result outputs for all images in the project merged in a single CSV-file by clicking the “Download all merged” button above the table.

...

Info

Please note: For quantitative analysis you will be presented .csv or .xlsx files and .jpg files with visualizations. 

You have done a great job obtaining solid numeric data from your images!

...