how to productionize custom vision model using Azure MLOPS?
Hi, I have project requirement to build object detection model using company's dataset for manufacturing defects. I found custom vision is suitable, I trained , results look pretty good. But I have following questions to productionize this model. In…
OCR Demo on Vision Studio performs better than API call
I've been testing out Optical Character Recognition using Azure. However, I've noticed that the online demo version performs far better than the API version. In addition, the API model version is stuck on 2023-10-01 instead of the 2024 version shown in…
Quick Training on Azure Custom Vision has not been updated since 3 days
I am working on an Object detection project and I have been labeling images. I completed 4 iterations and the performance was gradually increasing as I kept adding images. But, on the 5th iteration..the performance page got stuck and has not been updated…
Azure Vision AI evaluation run error
Error: "1. Batch did not complete successfully. OutputResultWriteFailed: An unexpected error was encountered."
How to use the latest model version for Vision OCR on Python?
When I am using the ImageAnalysisClient in my code to analyze an image and return text, the API only seem to use the 2023-10-01 model version. How can I use 2024 or later version of the Vision OCR? Here is my current code: client =…
Getting a preview of the image passed to Computer Vision
Is there a way to see the image that was passed to Azure Computer Vision? I've passed an image from Android CameraX ImageAnalysis (ImageProxy) but I keep getting a 400 Bad Request response, saying: The image size is not allowed to be zero or larger than…
![](https://techprofile.blob.core.windows.net/images/QCfNlNRFF0SfiVaGz9IwxQ.png?8DC10D)
![](https://techprofile.blob.core.windows.net/images/QCfNlNRFF0SfiVaGz9IwxQ.png?8DC10D)
How can I programmatically use a custom model trained on Vision Studio?
I created a custom model on Vision Studio and want to test it programmatically in a Node.js app. I used the endpoint provided under the 'Resource Management' section of my Computer Vision resource. My script is configured to use the 'Tags' feature, but…
Azure Services for Video Content Moderation
I have used several Azure services for content moderation, including Azure AI Computer Vision, Azure AI Content Safety, and Azure Video Indexer. Among these, only Video Indexer supports video moderation directly, but it also provides features like…
How to find resource in Vision Studio
Hello, I am following the instructions from "Exercise - Classify images with an Azure AI Vision custom model". It seems smooth, and I successfully built a storage account and uploaded images to its container. However, I found I could not…
Migrating Azure Custom Vision Prediction API to V4.0 Image Analysis
Hi everyone, We're currently using V3.0 of the Azure Custom Vision Prediction API for Image Classification and Object Detection, along with V2.0 of the OCR Read function. In order to migrate from V3.0 to V4.0, I'm aware we need to move to Vision…
ow can I get access to GPU compute resources.
I am getting a message that states something about a quoto, when I try access GPU compute instances. I want to be able to use GPU compute.
![](https://techprofile.blob.core.windows.net/images/k3pGvNqV6k28ggaVHaTPrQ.png?8D803E)
Azure Computer Vision Resource not found when called using the SDK or accessed via the browser.
I created an Azure Computer Vision resource to explore its features. I'll be using it inside a mobile app and make use of the ImageAnalysis SDK: https://www.nuget.org/packages/Azure.AI.Vision.ImageAnalysis/1.0.0-beta.3. After I created the resource, I…
![](https://techprofile.blob.core.windows.net/images/QCfNlNRFF0SfiVaGz9IwxQ.png?8DC10D)
Vision Studio don't show my custom blob loaded images
In Vision Studio I selected the scenario "Search photos with image retrieval" and loaded my 76 jpeg images in a blob storage. The images seems to be correctly loaded and processed, Vision Studio only show icons and never the actual image,…
AI Vision v4 - when will adult content detection be available?
In the documentation, it says that Vision AI v4 doesn't currently include the adult content detection feature (it's only in v3.1); https://video2.skills-academy.com/en-us/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0 There's no news…
How to fix "Failed to set CUDA device 0!" on WSL2 when trying to run spatial analysis container?
I'm in the process of following the tutorial for setting up the spatial analysis container on a local desktop machine with Windows 11 and WSL2, using Ubuntu 18.04 LTS. Here is the documentation for the tutorial:…
Vision Studio Extract text from images "code": "404", message": "Resource not found
Hello, I'm trying to use Azure's own API to test Vision Studio, but when I click on "Use the REST API" I get a 404 error "Resource not found". I would like to know if there is a problem with Azure, the license, or something like that,…
How to use Azure Face API on RTSP streaming?
Hello, We checked the Azure Face API functionality. We got good accuracy value but its latency is so high on RTSP streaming as screen got freezes. Need support here how we can built this solution using Azure Face API with python.
![](https://techprofile.blob.core.windows.net/images/h9uX-Pd1CkeMXwJtZXwpRA.png?8DB079)
Is Azure OCR Compliant with GDPR?
I would like to use the Azure Vision to extract address data from postal envelopes. However, as this obviously contains identifying information, I am unclear if this would cause a GDPR breach. Assuming the client side is secure, and we're just talking…
![](https://techprofile.blob.core.windows.net/images/rnwqhQqer0-oefliFOISMA.png?8DC41C)
Computer Vision- Image width too small
I am trying to create a custom image classification project with Computer Vision. I have created the COCO dataset, resized all images to match the minimum requirements (256x256) and it stills raises the same error: Dataset: datasetincidentes,…
How can i change the input dimensions for spatial analysis container for processing live video feed?
I am processing a live stream on Desktop machine by making it an iotedge device using Azure Spatial Analysis container. The size of video frame that my camera produces is 704 x 576 and the person detector used in the container is around size 416 x 416. I…