Pinned Repositories
CLRS
Some exercises and problems in Introduction to Algorithms 3rd edition.
keras-bert
Implementation of BERT that could load official pre-trained models for feature extraction and prediction
keras-gpt-2
Load GPT-2 checkpoint and generate texts
keras-multi-head
A wrapper layer for stacking layers horizontally
keras-radam
RAdam implemented in Keras & TensorFlow
keras-self-attention
Attention mechanism for processing sequential data that considers the context for each timestamp.
keras-transformer
Transformer implemented in Keras
keras-xlnet
Implementation of XLNet that can load pretrained checkpoints
toolbox
https://cyberzhg.github.io/toolbox/ Encoding and parsing tools.
torch-multi-head-attention
Multi-head attention in PyTorch
CyberZHG's Repositories
CyberZHG/keras-bert
Implementation of BERT that could load official pre-trained models for feature extraction and prediction
CyberZHG/toolbox
https://cyberzhg.github.io/toolbox/ Encoding and parsing tools.
CyberZHG/keras-self-attention
Attention mechanism for processing sequential data that considers the context for each timestamp.
CyberZHG/CLRS
Some exercises and problems in Introduction to Algorithms 3rd edition.
CyberZHG/keras-transformer
Transformer implemented in Keras
CyberZHG/keras-radam
RAdam implemented in Keras & TensorFlow
CyberZHG/keras-multi-head
A wrapper layer for stacking layers horizontally
CyberZHG/keras-xlnet
Implementation of XLNet that can load pretrained checkpoints
CyberZHG/keras-gpt-2
Load GPT-2 checkpoint and generate texts
CyberZHG/keras-transformer-xl
Transformer-XL with checkpoint loader
CyberZHG/keras-gcn
Graph convolutional layers
CyberZHG/keras-layer-normalization
Layer normalization implemented in Keras
CyberZHG/keras-pos-embd
Position embedding layers in Keras
CyberZHG/keras-word-char-embd
Concatenate word and character embeddings in Keras
CyberZHG/keras-gradient-accumulation
Gradient accumulation for Keras
CyberZHG/keras-octave-conv
Octave convolution
CyberZHG/keras-ordered-neurons
Ordered Neurons LSTM
CyberZHG/keras-drop-block
DropBlock implemented in Keras
CyberZHG/keras-adaptive-softmax
Adaptive embedding and softmax
CyberZHG/keras-trans-mask
Remove and restore masks for layers that do not support masking
CyberZHG/keras-embed-sim
Calculate similarity with embedding
CyberZHG/keras-losses
Some loss functions in Keras
CyberZHG/keras-position-wise-feed-forward
Feed forward layer implemented in Keras
CyberZHG/keras-conv-vis
Convolution visualization
CyberZHG/keras-bi-lm
Train the Bi-LM model and use it as a feature extraction method
CyberZHG/swift-6502-core
Emulation of the 6502 CPU
CyberZHG/keras-piecewise
A wrapper layer for splitting and accumulating sequential data.
CyberZHG/keras-piecewise-pooling
Piecewise pooling layer in Keras
CyberZHG/CyberZHG
CyberZHG/mos-6502-restricted-assembler
A 6502 assembler with restricted functions