Deep Learning with PyTorch

Value normalization

It is a common practice to normalize features before passing the data to any machine learning algorithm or deep learning algorithm. It helps in training the algorithms faster and helps in achieving more performance. Normalization is the process in which you represent data belonging to a particular feature in such a way that its mean is zero and standard deviation is one.

In the example of dogs and cats, the classification that we covered in the last chapter, we normalized the data by using the mean and standard deviation of the data available in the ImageNet dataset. The reason we chose the ImageNet dataset's mean and standard deviation for our example is that we are using the weights of the ResNet model, which was pretrained ...