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.
neural-network tensorflow gpu word2vec word-embeddings gpu-acceleration gpu-tensorflow cosine-similarity glove glove-embeddings tensorflow-layers
-
Updated
Oct 13, 2018 - Jupyter Notebook