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

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))))

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

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.

Better integration with VOTT.

Add Custom Vision import/export

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!!!!!

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.

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

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

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!)

see title

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

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.

Hi, I am new to custom vision services, I followed along image classification documentation, which is very nice and straight forward. I had some trouble connecting it with my azure subscription to remove limited trial but some how I did it. After doing so, I cannot create a new Object Detection project on my azure resource: "Object detection is on preview, use limited trail resource..".
I think something is missing from documentation about these details. Need some help on this.
Thanks.

Btw, I am working on a test with Azure Functions. Would be nice to see a tutorial on Custom Vision + Functions.

This would be useful when organizing mass datasets that have duplicate images. i.e. web applications with unique IP addresses as filenames.

Lifting the restrictions, such as max number of predictions or training iterations, so that it would become flexible for variety of projects such as real-time video analysis.

Setting constraints for exported model size. The model size usually seems to be below 3MB but I would like to control this factor a little more. What if I want to add several models to my application but I don't want it to get bulky.