Name: Dr. Yong CHENG
Type: User
Company: WeBank
Bio: Senior Researcher and Team Leader.
Specialities: Programming (Python, C/C++), Math (optimization).
PhD (TU Darmstadt), MPhil (HKUST), B.Eng. (ZJU)
Location: Shenzhen, PR China
Dr. Yong CHENG's Projects
text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network
TextBoxes++: A Single-Shot Oriented Scene Text Detector
A synthetic data generator for text recognition
tf.keras + tf.data with Eager Execution
tf-trusted allows you to run TensorFlow models in secure enclaves
Train TensorFlow models on YARN in just a few lines of code!
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Time-series Generative Adversarial Networks (fork from the ML-AIM research group on bitbucket))
Experiments on unsupervised anomaly detection using variational autoencoder. The variational autoencoder is implemented in Pytorch.
MLP_VAE, Anomaly Detection, LSTM_VAE, Multivariate Time-Series Anomaly Detection, IndRNN_VAE, Tensorflow
Lstm variational auto-encoder API for time series anomaly detection and features extraction
6.857 project - implementation of scheme for encrypting integer vectors that allows addition, linear transformation, and weighted inner products.
vertical federated learning paper lists
Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Fast parallel CTC.
A few exercises for use at events.
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow
YASL (Yet Another Simple library) is a C++ library contains modules and utilities which other Secretflow code depends on.
A simple, fully convolutional model for real-time instance segmentation.