CyberZHG
CyberZHG
keras-bert
Implementation of BERT that could load official pre-trained models for feature extraction and prediction
keras-self-attention
Attention mechanism for processing sequential data that considers the context for each timestamp.
keras-xlnet
Implementation of XLNet that can load pretrained checkpoints
keras-multi-head
A wrapper layer for stacking layers horizontally
keras-radam
RAdam implemented in Keras & TensorFlow
CLRS
Some exercises and problems in Introduction to Algorithms 3rd edition.
keras-gpt-2
Load GPT-2 checkpoint and generate texts
keras-transformer
Transformer implemented in Keras
torch-multi-head-attention
Multi-head attention in PyTorch
keras-adabound
AdaBound optimizer in Keras