Review of paper 'An Image is Worth More Than 16x16 Patches'

Review of paper 'An Image is Worth More Than 16x16 Patches' and introduction to the pixel transformer.
Chee Yeo
August 30, 2024 machine-learning computer-vision python

Notes on using AWS Textract

Notes on using AWS Textract to process expense data
Chee Yeo
May 22, 2024 aws textract ocr machine-learning computer-vision

On using airflow to preprocess vision dataset

An example of using airflow to preprocess computer vision dataset
Chee Yeo
May 19, 2024 airflow machine-learning opencv computer-vision ocr pytorch

Self-hosted runners and automated Docker build

Running self-hosted runners to build and deploy docker containers from github actions
Chee Yeo
November 6, 2023 computer-vision opencv github-actions self-hosted-runners terraform research

Guide to training your own object detector using the TFOD API V2

Pain-free guide to using the TFOD API
Chee Yeo
November 3, 2021 machine-learning deep-learning computer-vision tensorflow