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. Additional Documentation - Object Detection Model Export

    Hello,

    Could you please provide detailed documentation regarding the integration of an exported model to CoreML. Currently, the model registers an output of a multi-dimensional array. Can the output be more defined so that it is more clear when integrated into iOS.

    5 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 →
  2. How can we create a negative tag using the API ?

    I see that we can change the type (negative or non-negative) using the UI interface but not with the API.

    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 →
  3. change the Dockerfile to include the -u for logging

    The Dockerfile, when exporting a Linux Container, has the command:

    CMD python app.py

    this is buffering the output of the app.py command, so you do not see the logged items as needed.

    If you change this to:

    CMD python -u app.py

    It will not buffer the output.

    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  ·  Samples & SDKs  ·  Flag idea as inappropriate…  ·  Admin →
  4. Ability to give each image a name.

    Ability to give each image a name via the UI. Display that name when hovering over the image in the UI rather that displaying "open image detail". I have a lot of similar looking images and I want to name them by the date they were taken but I don't want the date to be a tag.

    You also need a category of UI on your suggestions box.

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

    We’ll send you updates on this idea

    2 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
    Under Review  ·  Luke Bayler responded

    Thanks for the suggestion. Just a couple of days ago we added a category for UI suggestion.

  5. Detect abstract patterns

    It would nice to be able to detect patterns suchs as "circles, rectangles, triangles" etc from the image. This way we could describe for example mattresses and curtains semi-automatically with vision API.

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

    We’ll send you updates on this idea

    0 comments  ·  Image Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  6. Provide feature to changes subscription mapped with project

    Provide feature to changes subscription mapped with project.

    If we moved azure custom vision resources in azure portal then it exiting project not visible in portal.

    This is blocker need to fix. Project seems not working if subscription limit reached. Need to provide feature to change subscription mapping ASAP.

    Thanks, Great Api. Microsoft.
    Good Job.

    3 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 →
  7. Provide feature to download existing training images

    Provide feature to download existing training images

    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  ·  Training  ·  Flag idea as inappropriate…  ·  Admin →
  8. Provide clone project feature

    Provide clone project feature.
    Some time developer want to clone project and map with other Azure subscription.
    To create multiple environment like dev, test, stage, prod

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

    We’ll send you updates on this idea

    2 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  9. Display the endpoint in the Custom AI portal

    The SDK has been recently updated, and now the TrainingApi(trainingkey) class has been replaced by the CustomVisionTrainingClient(trainingkey, endpoint=endpoint) class.
    The only way to find the endpoint in the portal is to create a project.
    That doesn't help if you want to create the project programmatically using the SDK. Here's the code you would need to write:
    from azure.cognitiveservices.vision.customvision.training import CustomVisionTrainingClient

    trainer = CustomVisionTrainingClient(TRAINING_KEY, endpoint=ENDPOINT)

    Create a new project

    print ("Creating project...")
    project = trainer.create_project("My Project")

    However, I can't determine the ENDPOINT unless I've already created the project using the UI.
    At present, the Custom Vision preview only appears…

    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  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  10. tags

    Allow a tag to have a description ie a paragraph that describes what the tag is. This is different to the name, which is the only way currently to record info about the tag. The CustomVision.ai service should allow maintenance of the description and the API should pull back the description along with the name and score when accessing the predictions API.

    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 →
  11. 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 →
  12. 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 →
  13. 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 →
  14. 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 →
  15. 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 →
  16. 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 →
  17. 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 →
  18. 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 →
  19. 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 →
  20. 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 →
  • Don't see your idea?

Feedback and Knowledge Base