1. Learn
    2. /
  2. Courses
    3. /
  3. Deep Learning with PyTorch

Exercise

Torchvision module

You already finetuned a net you had pretrained. In practice though, it is very common to finetune CNNs that someone else (typically the library's developers) have pretrained in ImageNet. Big networks still take a lot of time to be trained on large datasets, and maybe you cannot afford to train a large network on a dataset of 1.2 million images on your laptop.

Instead, you can simply download the network and finetune it on your dataset. That's what you will do right now. You are going to assume that you have a personal dataset, containing the images from all your last 7 holidays. You want to build a neural network that can classify each image depending on the holiday it comes from. However, since the dataset is so small, you need to use the finetuning technique.

Instructions

100 XP
  • Import the module that lets you download state-of-the-art CNNs.
  • Download and load a pretrained ResNet18 network.
  • Freeze all the layers bar the final one.
  • Change the last layer to correspond to the number of classes (7) in your dataset.