After training, we can visualize our computational graph in TensorBoard, as shown in the following diagram. As you can see, our Model takes input, weights, and biases as input and returns the output. We compute Loss and Accuracy based on the output of the model. We minimize the loss by calculating gradients and updating weights. We can observe all of this in the following diagram:
If we double-click and expand the Model, we can see that we have three hidden layers and one output layer:
Similarly, we can double-click ...
