Deep Learning with PyTorch

Baseline model

Create a very simple model that beats the baseline score. In our previous example of dogs and cats, classification, the baseline accuracy should be 0.5 and our simple model should be able to beat this score. If we are not able to beat the baseline score, then maybe the input data does not hold the necessary information required to make the necessary prediction. Remember not to introduce any regularization or dropouts at this step.

To make the model work, we have to make three important choices:

• Choice of last layer: For a regression, it should be a linear layer generating a scalar value as output. For a vector regression problem, it would be the same linear layer generating more than one scalar output. For a bounding box, ...