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

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.

provide confusion matrices in model evaluation

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.

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"

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.

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.

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

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

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.

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

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.

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.

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

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?

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.

Please add the tensorflowjs model option.

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