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. export to azure registry

    It would be great if we could export our customvision ML directly into the Azure Container Registry

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

    We’ll send you updates on this idea

    0 comments  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  2. Bug when selecting images by clicking on the tick

    When I click the tick in the bottom left hand corner of the training image the image just shrinks briefly and the tick doesn't turn blue. To be able to get the tick to turn blue which means it is selected, I need to hold down the left mouse key when I click on the tick and then move the cursor back over the tick until it turns light gray. This makes selecting multiple images very time consuming and fiddly. I've tested on Chrome, Firefox and Edge and all 3 browsers have the same problem.

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  3. confusion matrix

    provide confusion matrices in model evaluation

    3 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 →
  4. Prompt for user confirmation before DELETE an iteration

    I've accidentally clicked the DELETE button of an iteration, and tragically it just got deleted without any confirmation from the user. Please prompt for user confirmation before DELETE an iteration.

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

    We’ll send you updates on this idea

    1 comment  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  5. Ability to add a description to training iteration

    When starting training, add a field that allows the user to input a description of that training iteration. Useful when trying different sets of images, or a different types of images

    "Using more samples from pre-processing type X"

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  6. Flip images horizontally for detection of relative directions

    I'm trying to train a model to recognize whether the camera is facing left or right. The ability to flip images horizontally would be helpful.

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  7. Flip images horizontally for detection of relative directions

    I'm trying to train a model to recognize whether the camera is facing left or right. The ability to flip images horizontally would be helpful.

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  8. Fix bug: Cannot open the project after iteration Published error

    Fix bug in Web UI: after iteration Published error when deleting a project, I cannot click open the project until I refresh the page.

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  9. be able to zoom

    Please enable zooming in on an image to tag small features in training.

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

    We’ll send you updates on this idea

    1 comment  ·  Training  ·  Flag idea as inappropriate…  ·  Admin →
  10. Allow retraining of image classification model via Python

    The custom vision documentation contains an example of how to create and train an image classification model then use it to make predictions, all in Python. It would be useful to be able to retrain already existing models using additional images in Python, as this can currently be done when viewing projects on the website but when attempting to retrain via Python just creates a new project with only the new images.
    There is also the issue that when training, training can only be completed when there are images present for all tags created, otherwise the error "CustomVisionErrorException: Not enough…

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

    We’ll send you updates on this idea

    0 comments  ·  Training  ·  Flag idea as inappropriate…  ·  Admin →
  11. Rotate Images within Training Images page

    Ability to Rotate images within the Training Images area. Some of my images show with correct orientation within Windows but are rotated within Custom Vision while tagging. Might need some ability on the inference side to automatically orient images before performing inference.

    3 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 →
  12. export onnx model to set input size

    I have export a onnx model but found it's input size is 3416416
    Is it possible to set the input size for onnxruntime 1.0 to use?
    Same model is workable in onnxruntime 0.5, but not work in onnxruntime 1.0

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

    We’ll send you updates on this idea

    0 comments  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  13. Web UI: enable filter by subscription and saving the 'Resource' filter

    Unable to filter projects by subscription, which means I'm seeing a lot of projects by default in my portal when I log in for whichever subscription I may be a part of.

    There is a 'Resource' filter on the web ui, but no way to persist, save that filter. So every time you go back to the UI you end up with a full list of projects which may not be yours.

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

    We’ll send you updates on this idea

    0 comments  ·  Web UI  ·  Flag idea as inappropriate…  ·  Admin →
  14. Exporting Tensorflow model for Object detection

    There seems to be some new updates for exporting an object detection model. I am unable to export a TF model with or without specifieng the flavor using .net sdk. Once i try that from the sdk, that itteration also gets stuck in the exporting model for ever even in the CustomVision portal.

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

    We’ll send you updates on this idea

    1 comment  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  15. Export CoreML3 model

    Could you please support CoreML3 model format.
    To improve the implementation of object detection models in iOS apps.

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

    We’ll send you updates on this idea

    0 comments  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  16. Smart Labeler Preference

    The following public information does not hit with the string "Smart Labeler".

    <https://docs.microsoft.com/bs-cyrl-ba/azure/cognitive-services/custom-vision-service/suggested-tags>

    I know it's synonymous with "Suggested Tags," but people who don't know this feature get confused because web portal settings page displays it as "Smart Labeler Preference".
    Could you fix the document so that you can search in Smart Labeller?

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

    We’ll send you updates on this idea

    0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  17. measure object geometry in image

    Can custom vision measure object geometry from images? Since the face recognition service can identify and create polygons of face features, one may consider custom vision can do the same for specified features. Extract those polygons with some reference dimension units. The object of interest can be represented by the polygons and the dimensions can be approximated or estimated. Then use custom vision to quantify object size.

    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 →
  18. export tensorflowjs model

    Please add the tensorflowjs model option.

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

    We’ll send you updates on this idea

    0 comments  ·  Model Exporting  ·  Flag idea as inappropriate…  ·  Admin →
  19. endpoint

    It's so irritating not able to get an endpoint after train a model

    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  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  20. Exporting the Custom Vision Projects

    Hi ,

    We have tried the other options of exporting the Custom Vision Model

    It appears that , when models are exported from Custom Vision Projects , those may be built in the older versions

    For Azure ML :

    We are unable to find the steps shared in the zip file
    I am able to create the image with latest version of Azure ML but while publishing as a service model crashes as this could be due to models created in older version.

    For Tensorflow:

    Though I have updated it to the latest version Tensorflow 2.0 , the documentation shared…

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

    We’ll send you updates on this idea

    0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1 3 4 5 6 7 8
  • Don't see your idea?

Feedback and Knowledge Base