Fine-Tuning Vision Transformer for Retina Image Classification - Inference on Azure ML AKS

Explore fine-tuning a Vision Transformer (ViT) for diabetic retinopathy detection using the EyeQ dataset, a subset of the EyePacs dataset from the Kaggle competition. Learn how to leverage a pre-trained model by Google, initially trained on the ImageNet 21k dataset, and adapt it for retinal image classification. Discover the process of creating an Azure ML Managed Inference Endpoint backed by Azure Kubernetes Service (AKS) for efficient model deployment and inference. This 37-minute video, part of a 4-video series, provides hands-on guidance for machine learning engineers and data scientists interested in computer vision applications in healthcare. Access accompanying notebooks on GitHub to follow along and implement the techniques demonstrated.

LLMOPS :Fine Tune ViT Classifier Retina Images. Inference Azure ML AKS #machinelearning #datascience