guillaume-chevalier/GloVe-as-a-TensorFlow-Embedding-Layer
Taking a pretrained GloVe model, and using it as a TensorFlow embedding weight layer **inside the GPU**. Therefore, you only need to send the index of the words through the GPU data transfer bus, reducing data transfer overhead.
Jupyter NotebookMIT
Stargazers
- aatkinson@Microsoft , @maluuba
- ainvyuSamsung Electronics
- ajinkyaTTokyo
- alexgreenePlay
- beatgeek@cbsiamlg
- catree
- ceshine@veritable-tech
- cjiang2University of Alberta
- conan7882Research Scientist at Meta
- denisfitz57
- erohkohlLeipzig
- gnmarten
- haikarthiksskYugabyte
- hellcoderzComcast - Voice Search for Xfinity - Natural Language Processing
- ivan-bilanPersonio
- jiangplusshenzhen, china
- lekahaTokyo, Japan
- licheng1995Shanghai Jiao Tong University
- manhngodh
- MihailSalnikovNLP Group
- mrb1778Los Angeles, CA
- oudommeas
- PencroffDublin, Ireland
- roscopecoltran
- RussellZZ
- ryanbreedAustin, Tx
- sam-splat
- SamuelCabralCruzTicketmaster
- sideralRight here
- SijanC147Malta
- soojihanGermany
- TheMushrr00mgabrielcueto
- Thunderbottom@zerodha
- timhartillNeuralition
- vgrichinaNEAR Protocol
- wilber-guy