Hello everyone,

I want to celebrate that finally I have a part-time dream job as a coffee barista, and I am on my way of training (well, not that kind of training of course). If you ever met me in person, maybe your impression from my look is not about someone working as an AI product researcher. I drink coffee a lot and hanged out with fellow coffee enthusiast.

Image for post
Image for post
Photo by Nathan Dumlao on Unsplash

Following my previous publication on creating an end-to-end coffee picture classifier on docker–which you can deploy it later on Render, I want to inform you a good news. …

Hi! so I got promoted to a new position in my company to handle NLP and NLU problems since previously spent my time in the computer vision department. I am not actually fresh into this area, since I was previously exposed to RNN in the deep learning university course. I think I was just outdated with researches in this field, but I am trying to catch up recently.

Yes, I love Kaggle!

So I started to compete in one of the NLP starter competition, Real or Not? NLP with Disaster Tweets. This competition aims to identify whether a tweet is…

Image for post
Image for post
Photo by Alesia Kazantceva on Unsplash


Months ago, I started to use Fast.ai for deep learning. The course was very lightweight and intelligible. The course also covered image classification deployment, which classifies teddy bears, grizzly bears, and black bears. What I did was to modify it as a coffee classification problem. As simple as that, because I am working part-time as a barista and I love coffee so much. I just forced to code because the world demands you to code a little bit for making such great things. So, don’t call me a programmer (yes, I hate it).

I tried it locally on Docker and…

Hi, following my previous post about YOLOv3 object detection below

And this time I jumped into YOLOv5 (yes I tried the v4, but not yet hyped so I tried the v5) for object detection.

YOLOv5 has pretrained model which included 80 classes as the previous model has. I found that the way YOLOv5 presented in PyTorch is very similar to the Darknet version, although controversially this one seems like a PyTorch implementation from previous version but lighter (spill some tea, the original YOLO ended in v3). Here is the Ultralytics YOLOv5 repositories.

Make sure to clone the repo to your…

This time I will write about Darknet and YOLO Object Detection, and some tutorial on it. I knew them from humanoid robot research, which needs computer vision and machine learning to detect an object. Since I am a big fan of C++ (to differ me upon what so-called as “modern-time data scientist hype guys”, I know how to code in C++ and actually I am fast). I am a big fan of this model, and I would like to introduce it.


To install darknet: https://pjreddie.com/darknet/install/

Yolo is a real-time object detection system. It uses the dataset to train what contained…

Salman A. F. Chen

A coffee enthusiast

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store