Vo Van Tu's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
awesome-mlops
A curated list of references for MLOps
Learning-to-See-in-the-Dark
Learning to See in the Dark. CVPR 2018
Awesome-Vision-Attentions
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
torchmetrics
Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.
ai-tech-interview
๐ฉโ๐ป๐จโ๐ป AI ์์ง๋์ด ๊ธฐ์ ๋ฉด์ ์คํฐ๋ (โญ๏ธ 1k+)
Invertible-ISP
[CVPR2021] Invertible Image Signal Processing
R-CNN_LIGHT
Regional-Convolution Neural Network for blink detection based on contouring.
ml_in_production
A set of demo of deploying a Machine Learning Model in production using various methods
color-aware-style-transfer
Reference code for the paper CAMS: Color-Aware Multi-Style Transfer.
multi-task-defocus-deblurring-dual-pixel-nimat
Reference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the networkโs ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~ 39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task.
tensor_svd
A tensor based approach to svd for dimensionality reduction and noise reduction
Poisson-image-editing
Matlab implementation of Poisson image editing
white-box-layer
Deep Learning Package based on TensorFlow.