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
Issues
- 1
Shapes of both tensors are mismatching
#1 opened by Dhawaleswrar - 1
Loading Tensor
#2 opened by suatfk - 0
Fix the latex
#5 opened by guillaume-chevalier - 0
Fix `encoding="utf8"` on the file open() for the code to work in Windows
#3 opened by guillaume-chevalier - 0
Refactor to a class to be able to reuse the code more easily outside of the notebook
#4 opened by guillaume-chevalier