Training this model and evaluating the accuracy on the validation set (0.802000) lets us appreciate that a larger model bought us an increase in accuracy, but not that much. The accuracy on the...

Hello help Data science

Extracted text: Training this model and evaluating the accuracy on the validation set (0.802000) lets us appreciate that a larger model bought us an increase in accuracy, but not that much. The accuracy on the training set is practically perfect (0.998100). What is this telling us? That we are overfitting our model in both cases. Our fully connected model is finding a way to discriminate birds and airplanes on the training set by mem- orizing the training set, but performance on the validation set is not all that great, even if we choose a larger model. PyTorch offers a quick way to determine how many parameters a model has through the parameters () method of nn. Model (the same method we use to provide the parameters to the optimizer). To find out how many elements are in each tensor instance, we can call the numel method. Summing those gives us our total count. Depending on our use case, counting parameters might require us to check whether a parameter has requires_grad set to True, as well. We might want to differentiate the number of trainable parameters from the overall model size. Let's take a look at what we have right now: