Duong Tran Thanh's repositories
mllib-from-scratch
Building a Machine Learning Library from scratch using Python3, based on SOTA library Scikit-learn
FPTU-Learning-Resources
Learning Resources Sharing FPTU campus HCMC (Artificial Intelligence)
vireceipt-information-extraction
AI application for extracting information from Vietnamese-language's receipt
bi-kip-hanh-nghe-coder
Reusable code snippets for enhancing work
duongttr.github.io
Build a Jekyll blog in minutes, without touching the command line.
Image-Captioning-Transfromers
Image Captioning task using Vision Transformer
sudoku-solver-detection-fastapi
Detecting and Solving Sudoku board using TF Keras model, FastAPI and Heroku deployment
video-colorization-baseline-models
Collection of many baseline models for video colorization task (fixed to run correctly and guided documents)
arcface_tf2
ArcFace unofficial Implemented in Tensorflow 2.0+ (ResNet50, MobileNetV2). "ArcFace: Additive Angular Margin Loss for Deep Face Recognition" Published in CVPR 2019. With Colab.
artistic-videos
Torch implementation for the paper "Artistic style transfer for videos"
Coursera-Deep-Learning
My notes / works on deep learning from Coursera
facenet-pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
file-space
Space to store files
labinfras
Build a working infrastructure for a small Machine Learning software development team
Mathematics-for-ML
๐งฎ A collection of resources to learn mathematics for machine learning
ML-GCN
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
morethan-log
Visit my blog ๐
poe-api
A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.
segmenter
[ICCV2021] Official PyTorch implementation of Segmenter: Transformer for Semantic Segmentation
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
VideoFlow
Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors