---
title: "naphatthara (@Naphatthara) | Hashnode"
description: "ML Engineer & Solution Architect · Deep tech, real impact, every phase from research to production. Read the latest articles by naphatthara on Hashnode."
url: "https://hashnode.com/@Naphatthara"
---

@Naphatthara

# naphatthara

@Naphatthara · Tokyo, Japan · Joined May 2026

ML Engineer & Solution Architect · Deep tech, real impact, every phase from research to production

[Website](http://naphatthara.dev/)

### [From Research to Production: The Benchmark Said 15 FPS. My Environment Said 10. Dependency Versions Said Nothing. 😑](https://naphatthara.dev/from-research-to-production-the-benchmark-said-15-fps-my-environment-said-10-dependency-versions-said-nothing?utm_source=hashnode&utm_medium=feed)

In my previous post, I wrote about bridging the gap between research code and production systems. This one is about something I did not pay enough attention to — until I had to. 😅 Library versions. Y

5 min read · [naphatthara.dev](https://naphatthara.dev/from-research-to-production-the-benchmark-said-15-fps-my-environment-said-10-dependency-versions-said-nothing?utm_source=hashnode&utm_medium=feed)

[May 24](https://hashnode.com/posts/from-research-to-production-the-benchmark-said-15-fps-my-environment-said-10-dependency-versions-said-nothing/6a12db40551486ce6cf661c2)

### [How to Understand Latency in Computer Vision Inference Systems](https://naphatthara.dev/how-to-understand-latency-in-computer-vision-inference-systems?utm_source=hashnode&utm_medium=feed)

In real-time computer vision systems, latency is not just a metric — it is a constraint tied directly to safety and user experience. I've worked on systems where end-to-end latency — from receiving st

5 min read · [naphatthara.dev](https://naphatthara.dev/how-to-understand-latency-in-computer-vision-inference-systems?utm_source=hashnode&utm_medium=feed)

[May 23](https://hashnode.com/posts/how-to-understand-latency-in-computer-vision-inference-systems/6a11cd401a3cf7bffc35aff6)

### [From Research to Production: What Code Needs Before It Can Ship](https://naphatthara.dev/from-research-to-production-what-code-needs-before-it-can-ship?utm_source=hashnode&utm_medium=feed)

If you've ever handed off research code to an engineering team — or received it — you probably know this moment. The model works. The accuracy is great. The paper is published or the PoC is approved.

9 min read · [naphatthara.dev](https://naphatthara.dev/from-research-to-production-what-code-needs-before-it-can-ship?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/from-research-to-production-what-code-needs-before-it-can-ship/6a11a32e1a3cf7bffc1e8dea) [May 23](https://hashnode.com/posts/from-research-to-production-what-code-needs-before-it-can-ship/6a11a32e1a3cf7bffc1e8dea)
