Exercise

Finetuning a CNN

Previously, you trained a model to classify handwritten digits and saved the model parameters to my_net.pth. Now you're going to classify handwritten letters, but you have a smaller training set.

In the first step, you'll create a new model using this training set, but the accuracy will be poor. Next, you'll perform the same training, but you'll start with the parameters from your digit classifying model. Even though digits and letters are two different classification problems, you'll see that using information from your previous model will dramatically improve this one.

Instructions 1/2

undefined XP
    1
    2
  • Create a new model using the Net() module.
  • Change the number of output units, to the number of classifications for letters.