Lesson 9 assignments

[cody]

As a general handy tip for people who may not have been around for session 1, I’m finding the graph visualization of models to be a really effective way of feeling like I understand what Keras is doing under the hood; Jeremy explains it in this post from last November, so I won’t re-invent the wheel there, except to ‘bump’ it here:

Model and training visualization

I figured I’d create a new thread to talk about ways people have found to visualize models, training, and results. I’ll start with a tip - you can visualize your model as follows (you’ll need to conda install pydot, and apt install graphviz): from IPython.display import SVG from keras.utils.visualize_util import model_to_dot SVG(model_to_dot(model).create(prog='dot', format='svg')) Here’s the definition of the movielens ‘bias’ model: [image]