Today I learned


  1. Unets are useful when the size of your outputs is similar to that of the input. So, any kind of generative modeling such as segmentation or decrappification.
    1. They don’t make sense for classification problems.
    2. Unets have a downsampling and upsampling path. These parts are also called encoder and decoder respectively.
  2. A layer in a neural network is always an affine function, such as a matrix multiplication, followed by a non-linearity, such as a relu.