Žiga Vaupot's Blog

On November 3rd, I delivered my presentation OCI Vision and Oracle Analytics: Just like a Box of Chocolates at Analytics and Data Oracle User Community (AnDOUC)  TechCast : OCI Vision is a self-service AI Service, which applies computer vision to analyze image-based content. It allows developers easily integrate pre-trained models into their applications with APIs or custom training models to meet their specific use cases. In our example, I will explore how to use OCI Vision service to create a custom-built model to detect pneumonia infected lungs on a fresh dataset of X-ray images. In this example, I am using rather large dataset of X-ray images found on Kaggle.com. Oracle Analytics is then used as a front-end tool to use the model to classify new images for pneumonia. What to expect to see in this presentation? In the first place, we will demonstrate and explore the whole process from “plain” X-ray image to identifying pneumonia infected lungs using OCI services: Gathering and stori

After 5 years, I was attending HROUG’22   (Croatian Oracle User Group) as a presenter delivering my latest Just Like a Box of Chocolate presentation: OCI Vision is a self-service AI Service, available in Oracle Cloud Infrastructure (OCI), which Oracle defines as a service that “applies computer vision to analyse image-based content. Developers can easily integrate pretrained models into their applications with APIs or custom train models to meet their specific use cases. These models can be used to detect visual anomalies in manufacturing, extract text from documents to automate business workflows, and tag items in images to count products or shipments”. Basically, what Vision AI Service does is Image Classification, Object Detection and Document AI. In the first part, presentation focuses on how to prepare data for the training, by using Data Labelling, another OCI service, and how to run the model training itself using OCI Vision. In the second part of the presentation, we will focu

Many companies which are using Oracle Business Intelligence (OBI) for business analytics are faced with the dilemma of how to advance their analytics solutions and which business analytics tool strategy should they define and follow. Decision what to do usually has a long-term effect and is not always easy.  In case of OBI, there was quite a lot of uncertainties for several years. The tool itself didn’t see many changes and (major) updates. If there were any, such as Mobile Apps Developer (MAD), these were not particularly successful and have proved as "dead end". Oracle BICS (BI Cloud Service) was also a kind of failure as it was never became a successful product. It is not a surprise that many OBI users, even though they invested a lot into Dashboards or BI Publisher reports decided to abandon OBI in favour of new tools such as such as Tableau or PowerBI.  Oracle Analytics is a successor of Oracle Business Intelligence It is funny, but I’ve spoken to many OBI users who were

Oracle Analytics  September 2022 Update  has just came out. At least our instance got patched over the last night.  There are two major updates in this release, which I plan to cover in my future posts: The first new feature relates to the usage of REST APIs . Oracle Analytics can now connect to REST API data sources , such as Saas or PaaS applications. This feature is still in Preview, but available. Speaking of REST APIs, there is another nice feature that addresses snapshot management and data loading .  Snapshots (BAR files) can be now managed   programmatically using REST APIs. Similarly developers can programatically load their data for datasets using REST APIs. I believe both features will be welcomed by developers community. Even bigger, really MAJOR update is Semantic Modeller which will one day eventually replace good old BI Administration Tool . Semantic Modeller was available for Preview (and it still is) in July update. We, at Qubix have been involved with testing S

In my blog post Oracle AI Vision: Just like a Box of Chocolates I am discussing how to create a custom machine learning model for pneumonia image classification (can an image provided be classified as normal or infected lungs) using Oracle’s OCI Vision AI service for code-less image classification machine learning model.  In this post, I am taking the model created during my previous exercise and plugging it into Oracle Analytics in order to make predictions from there using self-service Oracle Analytics tools such as Data Flows and Data Visualisation. But before we can start using OCI Vision models in Oracle Analytics, there is a small amount of setup work to be done. Note : Oracle documentation for Analytics Cloud contains very good guidance on how to set everything up. You can find this document here . My example below mostly follows that document, however use case is different and there are one or two things which the original document is not mentioning (safe domains, plugins). Se

This little exercise started a few weeks back. What we tried to test is how Oracle AI Vision performs on a larger database for real. In order to perform this little test we used Chest X-Ray Images (Pneumonia)   dataset from kaggle.com . Let me begin with the following note:  We built the model as described below, but then we encountered an error which caused all the images to be classified as “pneumonia ” .  In the same time we had an opportunity to work closely with Oracle AI Services development team who have responded instantly and successfully removed the bug. And here are the results. Train The process of training the model is code free . Similarly as described in one of my previous blog posts , we needed a new custom project. Project acts as a container which can contain several models we created. There is a wizard that helps users to create a new one. The wizard is executed in three steps.  In the first step, basic parameters are set, such as the type of the model. In our case