keras-bi-lm

Last released Jan 22, 2022

Train the Bi-LM model and use it as a feature extraction method

keras-gcn

Last released Jan 22, 2022

Graph convolutional layers

keras-drop-block

Last released Jan 22, 2022

DropBlock implemented in Keras

keras-gpt-2

Last released Jan 22, 2022

GPT-2

keras-word-char-embd

Last released Jan 22, 2022

Concatenate word and character embeddings in Keras

keras-ordered-neurons

Last released Jan 22, 2022

Unofficial implementation of ON-LSTM

keras-octave-conv

Last released Jan 22, 2022

Octave convolution

keras-xlnet

Last released Jan 22, 2022

XLNet implemented in Keras

keras-trans-mask

Last released Jan 22, 2022

Transfer masking in Keras

keras-transformer-xl

Last released Jan 22, 2022

Transformer-XL implemented in Keras

keras-adaptive-softmax

Last released Jan 22, 2022

adaptive-softmax implemented in Keras

keras-rectified-adam

Last released Jan 22, 2022

RAdam implemented in Keras & TensorFlow

keras-bert

Last released Jan 22, 2022

BERT implemented in Keras

keras-transformer

Last released Jan 22, 2022

Transformer implemented in Keras

keras-position-wise-feed-forward

Last released Jan 22, 2022

Feed forward layer implemented in Keras

keras-embed-sim

Last released Jan 22, 2022

Calculate similarity with embedding

keras-pos-embd

Last released Jan 22, 2022

Position embedding layers in Keras

keras-layer-normalization

Last released Jan 22, 2022

Layer normalization implemented in Keras

keras-multi-head

Last released Jan 22, 2022

A wrapper layer for stacking layers horizontally

keras-self-attention

Last released Jan 22, 2022

Attention mechanism for processing sequential data that considers the context for each timestamp

mos-6502-restricted-assembler

Last released Nov 28, 2021

A 6502 assembler with restricted functions

keras-lr-multiplier

Last released Jun 22, 2021

Learning rate multiplier

mixal

Last released Jan 4, 2021

MIX Assembly Language Simulator

keras-adabound

Last released Jul 11, 2020

AdaBound optimizer in Keras

torch-position-embedding

Last released Jul 11, 2020

Position embedding implemented in PyTorch

torch-layer-normalization

Last released Jun 6, 2020

Layer normalization implemented in PyTorch

keras-piecewise

Last released May 17, 2020

A wrapper layer for splitting and accumulating sequential data

keras-gradient-accumulation

Last released Oct 29, 2019

Gradient accumulation for Keras

keras-lookahead

Last released Sep 23, 2019

Lookahead mechanism for optimizers in Keras

tensorflow-radam

Last released Sep 23, 2019

RAdam implemented in Keras & TensorFlow

keras-radam

Last released Sep 23, 2019

RAdam implemented in Keras & TensorFlow

keras-on-lstm

Last released May 30, 2019

Unofficial implementation of ON-LSTM

keras-targeted-dropout

Last released May 27, 2019

Targeted dropout implemented in Keras

mxnet-octave-conv

Last released Apr 19, 2019

Octave convolution

keras-perturbation

Last released Mar 11, 2019

A demonstration of perturbation of data

torch-gpt-2

Last released Feb 26, 2019

GPT-2 implemented in PyTorch

torch-transformer

Last released Feb 26, 2019

Transformer implemented in PyTorch

torch-embed-sim

Last released Feb 26, 2019

Embedding similarity implemented in PyTorch

torch-multi-head-attention

Last released Feb 24, 2019

Multi-head attention implemented in PyTorch

wiki-dump-reader

Last released Feb 1, 2019

Extract corpora from Wikipedia dumps

keras-succ-reg-wrapper

Last released Feb 1, 2019

A wrapper that slows down the updates of trainable weights

toy-auto-diff

Last released Dec 13, 2018

Toy demonstrations of auto differentiations.