Recall that neural networks built in Gorgonia only take tensor.Tensors as inputs. Therefore, the labels will also have to be converted into tensor.Tensor. The function is quite similar to prepareX:

func prepareY(N []Label) (retVal tensor.Tensor) {
  rows := len(N)
  cols := 10

  b := make([]float64, 0, rows*cols)
  for i := 0; i < rows; i++ {
    for j := 0; j < 10; j++ {
      if j == int(N[i]) {
        b = append(b, 1)
      } else {
        b = append(b, 0)
      }
    }
  }
  return tensor.New(tensor.WithShape(rows, cols), tensor.WithBacking(b))
}

What we're building here is a matrix with N rows and ten columns. The specifics of why we build a matrix of (N,10) will be explored in the next chapter, but for now let's zoom into an imaginary row. Imagine the first label, (int(N[i])), is 7. The row will look like this:

[0, 0, 0, 0, 0, 0, 0, 1, 0, 0]

This is called a one-hot vector encoding. It will be useful to us later, and will expanded upon in the next chapter.