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

Exercise

Building convolutional networks

You are on a team building a weather forecasting system. As part of the system, cameras will be installed at various locations to take pictures of the sky. Your task is to build a model to classify different cloud types in these pictures, which will help spot approaching weather fronts.

You decide to build a convolutional image classifier. The model will consist of two parts:

  • A feature extractor that learns a vector of features from the input image,
  • A classifier that predicts the image's class based on the learned features.

Both torch and torch.nn as nn have already been imported for you, so let's get to it!

Instructions 1/3

undefined XP
    1
    2
    3
  • Define the feature_extractor part of the model by adding another convolutional layer with 64 output feature maps, the ELU activation, and a max pooling layer with a window of size two; at the end, flatten the output.