From the course: Deep Learning Foundations: Natural Language Processing with TensorFlow
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Projecting vectors using TensorFlow - TensorFlow Tutorial
From the course: Deep Learning Foundations: Natural Language Processing with TensorFlow
Projecting vectors using TensorFlow
- [Instructor] So after extracting the learn weights from them embedding layer, it's time to write the vectors and the metadata into files so that we can visualize these vectors in a 3D space on the TensorFlow projector. So the process is very simple, we are using the same collaboratory notebook that we used in the previous lesson. So first of all, we have imported all the libraries, APIs using the same dataset. IMDB reviews, segregated, the training and testing set prepared the data, then trained our model with the same configuration embedding layer, the first layer, the flatten, and then too dense layer. We've created our model, then the next step is to actually extract the weight. So we have first isolated our embedding layer. Then we extracted the weights from the gate_weights function. And then we looked at the weight shape which is basically vocabulary size. That is we have 10,000 different words in 16…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.