Name: Wahyu Rahmaniar
Type: User
Company: Tokyo Institute of Technology
Bio: My research interests include artificial intelligence, medical imaging, computer vision, image processing, and robotics.
Twitter: wahyurahmaniar
Location: Tokyo, Japan
Blog: https://wahyurahmaniar.github.io/
Wahyu Rahmaniar's Projects
Implementation of PFLD For 68 Facial Landmarks By Pytorch
Progressive Growing of U-net+
An Android app which provides design news & inspiration as well as being an example of implementing material design.
Source codes for the paper "Learning Diverse Features with Part-Level Resolution for Person Re-Identification"
Pytorch implementation for Poly YOLO.
A video based fall detection approach and a fall detection system on ROS based on single image.
Person ReID in Aerial Imagery
A deep learning-powered visual navigation engine to enables autonomous navigation of pocket-size quadrotor - running on PULP
Papers with code. Sorted by stars. Updated weekly.
:bar_chart: Benchmark multiple object trackers (MOT) in Python
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Speech Recognition with Python examples
Python sample codes for robotics algorithms.
A PyTorch implementation for paper Unsupervised Domain Adaptation by Backpropagation
Pytorch implementation of the paper Iterative fully convolutional neural networks for automatic vertebra segmentation accepted in MIDL2018.
MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
use yolov3 pytorch to train kitti
PyTorch ,ONNX and TensorRT implementation of YOLOv4
Hybrid Quantum-Classical Machine Learning in TensorFlow
Implementation of Image encoding in FRQI image model and reconstructing the image from the Quantum states,
RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
real time video stabilization using Kalman Filter
Simple application for recognition of vehicle license numbers
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Implementations of recent research prototypes/demonstrations using MONAI.
MS-Loss: Multi-Similarity Loss for Deep Metric Learning
Fast and accurate object detection with end-to-end GPU optimization