Name: Wenchao QI
Type: User
Company: Aerospace Information Research Institute, Chinese Academy of Sciences
Bio: Assistant Researcher at AIR, CAS, China. I'm mainly engaged in deep learning in Hyperspectral Computer Vision.
Location: No. 20, Datun Road, Chaoyang District, Beijing, China
Wenchao QI's Projects
Keras implementations of Generative Adversarial Networks.
Keras implementation of Graph Convolutional Networks
image regression in keras
image regression template with 'imageDataGenerator' augmentation
Image segmentation with keras. FCN, Unet, DeepLab V3 plus, Mask RCNN ... etc.
this is an implement of DenseNet using keras ,this project can do Remote sensing image classifiy or retrieval.I trained and evaluated this model on a dataset called PatternNet.
Keras library for building (Universal) Transformers, facilitating BERT and GPT models
The Tensorflow, Keras implementation of Swin-Transformer and Swin-UNET
Keras attention models including botnet,CoaT,CoAtNet,CMT,cotnet,halonet,resnest,resnext,resnetd,volo,mlp-mixer,resmlp,gmlp,levit,nfnets
Some Metric Implementation in Keras (Such as Pearsons Correlation Coefficient, Mean Relative Error)
RAdam optimizer for keras
Image Annotation Tool with Python.
Visualizing the the loss landscape of Fully-Connected Neural Networks
李宏毅《机器学习》笔记,在线阅读地址:https://datawhalechina.github.io/leeml-notes
《统计学习方法》的代码实现
NAS-guided Lightweight Multiscale Attention Fusion Network for Hyperspectral Image Classification
Code for visualizing the loss landscape of neural nets
Tensorflow/Keras-compatible implementation of https://github.com/tomgoldstein/loss-landscape
Efficient Neural Network Loss Landscape Generation
LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data
a implement of LSTM using Keras for time series prediction regression problem
LSTM-RNN Tutorial with LSTM and RNN Tutorial with Demo with Demo Projects such as Stock/Bitcoin Time Series Prediction, Sentiment Analysis, Music Generation using Keras-Tensorflow
Lung fields segmentation on CXR images using convolutional neural networks.
code for paper "(TGRS 2019) Hyperspectral Classification Based on Lightweight 3D-CNN with Transfer Learning"
周志华《机器学习》又称西瓜书是一本较为全面的书籍,书中详细介绍了机器学习领域不同类型的算法(例如:监督学习、无监督学习、半监督学习、强化学习、集成降维、特征选择等),记录了本人在学习过程中的理解思路与扩展知识点,希望对新人阅读西瓜书有所帮助!