Microsoft

Custom Vision Service

Welcome to the Custom Vision Service API Forum

Categories

API – Any ideas or feedback pertaining to features or enhancements to Custom Vision Service API.

Documentation – Any ideas or suggestions for the API Reference or Documentation.

Language Support – Submit a request to have a particular language supported.

Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.

Release Notes – Recently updated December 19.

  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Option to disable storing images predicted

    There should be a variable or header that can be sent with the prediction API call to specify that the image should NOT be saved past the initial classification/object detection.

    My use case: Want to make a game incorporating object detection, and while I love the ability to see the predictions and modify them to improve my dataset I really don't want to see people's nude photos of them messing around or anything personally identifiable.

    Aside from the result of the scan, I don't want anything to do with those images.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  2 comments  ·  Privacy  ·  Flag idea as inappropriate…  ·  Admin →
  2. Provide input and output names for tensorflow models

    For certain applications (Tensorflow in Unity3D), we need to know the inputname and outputname

    I found these for the models currently generated by this service to be:
    inputname: Placeholder
    output
    name: model_outputs

    I think it is useful for many devs to include this, and other information such as mean and image size when eporting to tensorflow graph.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  3. Unclear what "compact" model means

    When trying to click "export", it says I should select "compact" model, but there is no help or hint as of what that means, nor where I can do that.
    Pity, because the rest of the UX is very easy.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  4. Ability to annotate an uploaded image

    CustomVision service has the ability to upload an image and assign a label to it (either via UI or API). It would be very convenient if there was an ability to annotate an uploaded photo and mark areas with labels so one image can have multiple labels (either via UI or API). Something like VIA or LABELIMG doing that.

    And use metadata and annotations to improve predictions accuracy.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  5. A "Multiclass" equivalent for Object Detection projects

    I often find that an object is detected under multiple different tags, each with a slightly different bounding box.

    I'd like a feature where if there are two object detections, each with a similar bounding box location and size, only the highest confidence one is used.

    This will ensure that an object will be "one or the other", rather than "both", similar to the way multiclass works in classification projects.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  6. add COUNTING OBJECT service please

    please I need the ability to count objects within a picture

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  7. Could not predict model has LEFT/RIGHT side, such as left arrow / right arrow.......

    Could not predict model has LEFT/RIGHT side, such as left arrow / right arrow.......

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  8. Export to ONNX 2

    The 17763 release of Windows and WinML api's aren't compatible with current ONNX exports. Please update to avoid this error:

    Type Error: Type (map(string,tensor(float))) of output arg (loss) of node (ZipMap) does not match expected type (seq(map(string,tensor(float))))

    6 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  9. Allow tagged areas to be downloaded as images

    Would be great if we could download the image inside the bounding box, or perform OCR etc on the box.

    7 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  10. Limit JSON response to "tagName" with the highest probability

    I need the AI to return only the "tagName" with the highest probability (or a limited number by choise). This option should be possible to send along with the "Request parameter".
    There are no need to recieve a potential very large JSON string.

    This is the use case:
    I picture are uploaded to the AI to identify a specific item out of a large set of goods - this could be potentially mean hundreds of tags in use. The return JSON string will contain the prediction of all these tags, so it could be a very large JSON string.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  11. Intergration with VOTT

    Better integration with VOTT.

    Add Custom Vision import/export

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  12. Object Detection Project, LIEF training iteration limit or give more iteration quotes!!!

    We are industry subscriber, BUT under Object Detection project, we ONLY allow to have 10 iterations! PLEASE LIFT this limitation or GIVE more iteration quotes!!!!!

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  2 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  13. Project page refresh button

    It would be great if the Projects page had a refresh button. Currently I have to refresh the page and then choose the resource group again each time.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  14. when do you plan to increase the #tags/project? would be really helpful to know

    when do you plan to increase the #tags/project? would be really helpful to know

    6 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  15. Recognize Checkboxes

    While the text reader does a good job of finding text, it doesn't know what a checkbox is. Sometimes it sees the square as an "I" and sometimes as a "1" and sometimes other things or nothing at all.
    If it could figure out what is a checkbox and ideally the difference between an empty and checked checkbox, we'd really have something

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  16. Allow addition of text into the AI (or a new API)

    Include a new domain called "text". This should identify text in the images and allow us to then associate tags with different blocks of text.

    Alternatively, release CustomText.AI. The ease at which you can associate custom meaning to any image would be very helpful with text too (and I imagine a lot easier!)

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  17. 2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  18. Object Detection Api

    Possiblity to send via query string the Probability Threshold Filter to avoid having a big json

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  19. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  20. Classification Type

    Please add a parameter for this to your Create Project APIs. The only way I can see to set it is via the web portal.

    Thanks.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  • Don't see your idea?

Feedback and Knowledge Base