viethungluu's Projects
Anchor optimization for RetinaNet.
[ECCV 2020] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis
Co-teaching for metric learning
The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."
An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing work.
Python bindings for FFmpeg - with complex filtering support
Flask App - Styled with Bulma | FBHL
mixup: Beyond Empirical Risk Minimization
End-to-end one-stage CNNs for text detection and recognition based on RetinaNet
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation"
StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
Implementation of spatial transformer networks (STNs) in keras 2 with tensorflow as backend.
TernausNetV2: Fully Convolutional Network for Instance Segmentation
Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
Config files for my GitHub profile.
Deepsort with yolo series. This project support the existing yolo detection model algorithm (YOLOV8, YOLOV7, YOLOV6, YOLOV5, YOLOV4Scaled, YOLOV4, YOLOv3', PPYOLOE, YOLOR, YOLOX ).
A human detector and tracker, written in python, using YOLOv7 for detection and DeepSORT for tracking the detections from YOLO.