Learn how to fine-tune a Vision Transformer (ViT) classifier using retinal images and convert it to ONNX format in this 12-minute video tutorial. Explore the process of adapting a pre-trained Google model, initially trained on the ImageNet 21k dataset, for Diabetic Retinopathy (DR) detection using the EyeQ dataset, a subset of the EyePacs dataset from the Kaggle Diabetic Retinopathy Detection competition. Follow along as the instructor demonstrates the fine-tuning process and guides you through converting the resulting model to ONNX format, enhancing its portability and deployment options. Access the accompanying Jupyter notebook on GitHub to practice and implement the techniques covered in this third installment of a four-part series on machine learning and data science.
Fine-Tuning ViT Classifier with Retina Images and Converting to ONNX - Video 3
The Machine Learning Engineer via YouTube
Overview
Syllabus
LLMOPS :Fine Tune ViT Classifier with Retina Images. Convert to ONNX #machinelearning #datascience
Taught by
The Machine Learning Engineer
Related Courses
-
Fine-Tuning Vision Transformer for Diabetic Retinopathy Detection - Part 2
-
Fine-Tuning Vision Transformer for Retina Image Classification - Inference on Azure ML AKS
-
Fine-Tuning Vision Transformer Classifier for EyePacs Dataset Quality Model - Part 1
-
Fine-Tuning ViT Classifier for Retina Images and Converting to ONNX Format - Part 3
-
LLMOps: Converting Fine-Tuned ViT Classifier to ONNX for CPU Inference
-
Fine-Tuning ViT Classifier for Retinal Image Detection - Part 2 (Español)
