Dat Nguyen-Thanh's repositories
VietAI-Machine-Translation
Final project in VietAI-NLP02 course
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
composer
Train neural networks up to 7x faster
datnth.github.io
Cayman Blog is a Jekyll theme for GitHub Pages, based on Cayman theme
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
fastdup
fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.
FasterViT
FasterViT: Fast Vision Transformers with Hierarchical Attention
FloorplanTransformation
Raster-to-Vector: Revisiting Floorplan Transformation
Label-Planar-Graph
Label keypoint, edge as planar graph on image
Llama2-Custom-document-QA
Using open-source LLM Llama2 by Meta on local CPU inference for document question-and-answer
mot_neural_solver
Official PyTorch implementation of "Learning a Neural Solver for Multiple Object Tracking" (CVPR 2020 Oral).
netron
Visualizer for neural network, deep learning, and machine learning models
news-corpus-crawling-nlp-data
Corpus tiếng việt
norfair
Lightweight Python library for adding real-time multi-object tracking to any detector.
plan2scene
Official implementation of the paper Plan2Scene.
QAI-Hackathon-2022-SmartMenu
Solution for SmartMenu challenger at QAI hackathon 2022
scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
Track2_AICITY2022_Vehicle_Retrieval_SSM
🏆 The 1st Place Solution for AICity2022 Challenge Track2: Natural Language-Based Vehicle Retrieval.
Vietnamese-Inverse-Text-Normalization
Fintuned envibert for Vietnamese Inverse Text Normalization
visdom
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
Voice-classification
A simple project for Vietnamese voice classification
X-CLIP
An official implementation for "X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"
YOLaT-VectorGraphicsRecognition
Source Code of NeurIPS21 paper: Recognizing Vector Graphics without Rasterization
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors