Name: Perseus Xi
Type: User
Company: Honor Device Co., Ltd
Bio: Remote Sensing PHD , graduated from University of Science and Technology of China , interested in Object Decection, Segmentation, Machine Learning, Computer Vis
Location: ShenZhen China
Blog: https://scholar.google.com.hk/citations?hl=zh-CN&tzom=-480&user=O2fKV2cAAAAJ
Perseus Xi's Projects
PyTorch Neural Network eXchange
convert dataset to coco/voc format
(ICCV 2019) Uncertainty-aware Face Representation and Recognition
Demo and other Python3 code
Smart python
PyTorch implementation of AdaCos
Pytorch implementation of Center Loss
Classification with PyTorch.
Image-to-Image Translation in PyTorch
A quickstart and benchmark for pytorch distributed training.
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
pytorch structural similarity (SSIM) loss
Build your neural network easy and fast
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
A PyTorch implementation of MPIIGaze and MPIIFaceGaze
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Implementation of several algorithms in RL based on Prof. sutton's book
RepViT: Revisiting Mobile CNN From ViT Perspective
reinforcement learning
after using MultiNET++ finished the multi tasks,project the road pixels on the LIdar Map,finally ,extract and discribe the road boundary in the properly morphological shape
Champion solution of the PIRM2018 Challenge on Perceptual Image Enhancement on Smartphones (Track B: Image Enhancement)
SceneLib2 is an open-source C++ library for SLAM originally designed and implemented by Professor Andrew Davison at Imperial College London.
Tracking the latest progress in Scene Text Detection and Recognition: Must-read papers well organized
Calculate common metrics in semantic segmentation, PyTorch Implementation
Udacity Self-Driving Car Engineer Nanodegree
Improving Semantic Segmentation via Video Propagation and Label Relaxation