Myles Lee

Cross-platform desktop notifications for Claude Code/Codex/Gemini - Get alerts when tasks complete

World Press Monitor: open-source RSS atlas and feed validation pipeline for global news sources.

This collection of AI sub-agents for Claude Code leverages a powerful agent-assembler to dynamically generate a personalized and project-specific AI development team based on your unique tech stack.

Personal Homebrew tap for command-line tools

track your agents, skills, and tools usage - Analytics dashboard for Claude Code, Gemini CLI, Codex CLI, and OpenCode

personal website

Claude Code dashboard with usage stats, error analysis, and sharable feature

No description provided.

No description provided.

No description provided.

No description provided.

When I used haar detection, it could not find face, when the photos were not frontal. However, I could solve this problem by using dnn detection

Analyzed dataset from kaggle competition(RSNA-MICCAI Brain Tumor Radiogenomic Classification)

When I met overfitting in model, I used data augmentation to expand small data set. Eventually, I got a better result by using data augmentation.

In order to understand NLP, I tried to diagnose text classification with tf hub

I tried to figure out positive and negative comments on my Youtube videos. So, I used NLP to analyze comments. I set the main language as Korean, but you can try setting English as the main language.

It was my first data analysis from kaggle competition. You can see my insight of data. I tried to my best to understand data and to come up with creative hypothesis.