There is no benefit to visualization if you cannot make use of it, in terms of understanding how and what the model has learned. To gain a better intuition of what the model has learned, we will be using TensorBoard.
TensorBoard is a powerful tool that can be used to build various kinds of plots to monitor your models while in the training process, as well as building DL architectures and word embeddings. Let's build a TensorBoard embedding projection and make use of it to do various kinds of analysis.
To build an embedding plot in TensorBoard, we need to perform the following steps:
- Collect the words and the respective tensors (300-D vectors) that we learned in previous steps.
- Create a variable in the graph that will hold the tensors.
- Initialize the projector.
- Include an appropriately named embedding...
