zzd1992

Researcher & Developer on Machine Learning

Shenzhen, China

Pinned Repositories

Adversarial-Defense-by-Suppressing-High-Frequencies
An efficient adversarial defense method with strong insights which won the fifth place of the IJCAI-2019 Alibaba Adversarial AI Challenge.
Language:Python11 3 03
GBDTMO
Gradient boosted decision trees for multiple outputs. Better generalization ability, faster training and inference.
Language:C++41 5 188
GBDTMO-EX
Examples and experiments of GBDT for multiple outputs.
Language:Python10 3 111
Image-Local-Attention
A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.
Language:Python136 4 220
LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Language:C++0 2 00
Numpy-Pytorch-Bicubic
Matlab's bicubic resize on Numpy and PyTorch.
Language:Python7 2 21
taichi
Productive programming language for portable, high-performance, sparse & differentiable computing
Language:C++0 2 00
TexasCalculator
Calculate the probability for Texas Hold'em Poker in real time.
Language:C++0 1 00
Tracking
End-to-end tracking method with fft layer
Language:Python00

zzd1992/Image-Local-Attention
A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.
Language:Python136 4 220
zzd1992/GBDTMO
Gradient boosted decision trees for multiple outputs. Better generalization ability, faster training and inference.
Language:C++41 5 188
zzd1992/Adversarial-Defense-by-Suppressing-High-Frequencies
An efficient adversarial defense method with strong insights which won the fifth place of the IJCAI-2019 Alibaba Adversarial AI Challenge.
Language:Python11 3 03
zzd1992/GBDTMO-EX
Examples and experiments of GBDT for multiple outputs.
Language:Python10 3 111
zzd1992/Numpy-Pytorch-Bicubic
Matlab's bicubic resize on Numpy and PyTorch.
Language:Python7 2 21
zzd1992/LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Language:C++0 2 00
zzd1992/taichi
Productive programming language for portable, high-performance, sparse & differentiable computing
Language:C++0 2 00
zzd1992/TexasCalculator
Calculate the probability for Texas Hold'em Poker in real time.
Language:C++0 1 00
zzd1992/Tracking
End-to-end tracking method with fft layer
Language:Python00