A.I.

Qdrant Vector Database

2025-01-24

[…] AI systems are incredible—until you hit a data retrieval bottleneck. You’d need to search through millions of high-dimensional vectors, fast. Vector databases are built specifically for similarity search, allowing AI apps to find the most relevant data points in milliseconds. And…

A.I.

Pydantic AI with LLMs

2024-10-21

If you’ve been working with LLMs like GPT, LLaMA, or any of their cousins, you know how powerful they are. But you also know how messy things can get when you’re trying to wrangle their outputs into something structured and usable. Pydantic AI is a game-changer for anyone looking to bring order to…

Computer Vision

YOLO Object Detection & Architecture

2024-08-23

I recently took a deep dive into the YOLO (You Only Look Once) architecture. Originally introduced by Joseph Redmon in 2015, I think it completely changed the game for object detection. Instead of treating detection as a classification task on multiple regions, YOLO does everything in a single pass,…

Deep Learning

CIFAR-1O CNN

2024-05-23

Let’s walk through how to build a CNN from scratch using TensorFlow and Keras to classify images from the CIFAR-10 dataset. CIFAR-10 is a dataset containing 60,000 color images (32x32 pixels) across 10 classes. import tensorflow as tf from tensorflow.keras import layers, models from…

Machine Learning

LightGBM, XGBoost, and others

2024-05-19

I learned that gradient boosting is like training a student with a series of tutors. Each tutor focuses on the student’s weak spots, helping them improve step by step. In machine learning, gradient boosting works by training weak models (typically decision trees) sequentially, where each new model…

Computer Vision

DeepLabV3: Replace Video Background

2024-05-11

Let’s use DeepLabV3’s semantic segmentation to remove the background from a video and replace it with a new background. import cv2 import torch import torchvision.transforms as transforms from torchvision.models.segmentation import deeplabv3_resnet101 import numpy as np from…

NLP

NLTK & spaCy Cheat Sheet

2024-05-01

This cheat sheet provides a quick reference for common NLTP tasks using NLTK and spaCy in Python. I. NLTK (Natural Language Toolkit) import nltk from nltk.tokenize import word_tokenize, sent_tokenize from nltk.corpus import stopwords from nltk.stem import PorterStemmer, WordNetLemmatizer from…

Machine Learning

scikit-learn's Pipeline

2024-03-04

Continuing from the previous issue on data preprocessing, introducing scikit-learn’s Pipeline class. Pipeline is a powerful tool for streamlining machine learning workflows. It allows you to chain multiple data processing steps and a final estimator (model) into a single object. This…

Machine Learning

ML Preprocessing Cheat Sheet

2024-03-03

I learned that a huge chunk of a machine learning engineer’s time isn’t spent on building fancy models. it’s spent cleaning and prepping data. It is not so glamorous. But it is actually the secret sauce to making models perform well. This process, called preprocessing, involves filling in missing…

Deep Learning

MNIST with PyTorch + GradCAM

2023-08-18

import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader import torchvision.transforms as transforms import torchvision.datasets as datasets # Define a transform to normalize the data transform = transforms.Compose([ transforms.ToTensor(),…

Deep Learning

MNIST with Tensorflow

2023-08-18

import tensorflow as tf from tensorflow.keras import layers, models from tensorflow.keras.datasets import mnist from tensorflow.keras.utils import to_categorical # Load the MNIST dataset (train_images, train_labels), (test_images, test_labels) = mnist.load_data() # Preprocess train_images =…

Deep Learning

PyTorch Model Card Classifier

2023-03-05

Let’s learn through doing. In this notebook we will create an image classifier to detect playing cards. We will tackle this problem in 3 parts: […] Almost every pytorch model training pipeline meets this paradigm. import torch import torch.nn as nn import torch.optim as optim from…

Big Data

Hadoop, Airflow, Spark, Kafka

2022-07-24

Behind the scenes, companies track and analyze customer interactions to improve recommendations, optimize user experience, and ultimately, boost sales. The backbone of this system are these five: […] Let’s see how they work together in a typical customer behavior analytics system.…

SQL

Window Functions

2021-09-15

Window functions are a powerful feature in databases that allow you to perform calculations across a set of rows related to the current row. They are commonly used in SQL queries to analyze and aggregate data within a specific window or range. […] The basic syntax for using window functions…

Analysis & Insights

Indonesia's Earthquake Analysis

2021-01-01

This analysis delves into a comprehensive exploration of earthquake data spanning the years 2011 to 2020. Through descriptive statistics, spatial and temporal analyses, and clustering techniques, we aim to uncover insights into the distribution, trends, and categorization of earthquakes in…