LLMOps: Converting Fine-Tuned ViT Classifier to ONNX for CPU Inference
The Machine Learning Engineer via YouTube
Overview
Learn how to convert a fine-tuned Vision Transformer (ViT) classifier to ONNX format and perform CPU inference in this 22-minute tutorial. Explore the process of transforming a custom dataset-trained ViT model into ONNX, enabling efficient deployment and execution on CPU hardware. Gain hands-on experience with code examples and practical insights for optimizing machine learning models for production environments. Access the provided GitHub repository for complete code samples and delve into related resources from previous videos to enhance your understanding of image processing and model conversion techniques.
Syllabus
LLMOps: Convert Fine Tuned ViT classifier to ONNX and CPU inference #machinelearning #datascience
Taught by
The Machine Learning Engineer