ardianumam

Ardian Umam's repositories

Tensorflow-TensorRT

This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.

Language:Jupyter Notebook304 11 33

compilations

This repository contains compilation of some chosen topics.

Language:Jupyter Notebook39 2 1

Data-Mining-and-Big-Data-Analytics-Book

This repository is made for my book: "Data Mining and Big Data Analytics". It contains all the codes and the dataset used in the book.

Language:Jupyter Notebook27 4 1

tensorflow-yolov3

Pure tensorflow Implement of YOLOv3 with support to train your own dataset

Language:PythonMIT18 30

Machine-Learning-From-The-Scratch

This repository folder is intended for my video series "Machine Learning from The Scratch using Python" in my YouTube channel.

Language:Python17 60

PointMixSwap

This is the official repository of our ECCV 2022 paper, "Point MixSwap: Attentional Point Cloud Mixing via Swapping Matched Structural Divisions".

Language:Python10 20

BanknotesRecognition

Repository for our VCIP 2018 paper, 'A Light Deep Learning Based Method for Bank Serial Number Recognition'. It contains all the dataset with the code.

Language:Python3 2 1

Image-Processing-Computer-Vision-Video-Series

This repository folder is intended for my video series about "Image Processing and Computer Vision" in my YouTube channel.

Language:C++3 20

PartDistill

Language:Python300

dl-2020-final-project

This is the final project for the Deep Learning class, NCTU - Fall 2020. The objective is to build a robot to win a line-following competition. Our team won first place out of 10 teams.

Language:Python2 30

Kalman-Filters

Kalman filtering, also known as linear quadratic estimation (LQE), is an algorithm that uses a series of measurements observed over time, containing statistical noise and other inaccuracies, and produces estimates of unknown variables that tend to be more accurate than those based on a single measurement alone, by estimating a joint probability distribution over the variables for each timeframe. The filter is named after Rudolf E. Kálmán, one of the primary developers of its theory.

Language:Jupyter NotebookMIT1 10