Manually computing the euclidean norm of the difference between two MNIST images with PyTorch

1

I’ve been playing around with the MNIST dataset and PyTorch and have loaded my dataset like so:

#Loading the MNIST training and test data:

train_data = datasets.MNIST(
    root = 'data',
    train = True,                         
    transform = ToTensor(), 
    download = True,            
)
test_data = datasets.MNIST(
    root = 'data', 
    train = False, 
    transform = ToTensor()
)

what’s interesting to me is that I am thinking of these images as 28 by 28 matrices with each entry representing the shade of the pixel. So I wanted to compute the Euclidean distance between two images after flattening them, in particular, I defined the following function:

def wtrain(i,j):
   s = train_data.data[i]
   t = train_data.data[j]
   s = torch.flatten(s)
   t = torch.flatten(t)
   d = (s-t)/1000
   d = (torch.norm(d))**2
   return d

What’s weird is that wtrain[0,1] does not equal wtrain[1,0]?

I was wondering if anyone could see why or offer an alternative way to compute this distance.

2

Both output tensors are using their raw uint8 dtype since you are indexing the internal .data attribute in train_data.data[index] and the ToTensor transformation is thus skipped.

The subtraction in (s - t) will thus under/overflow and will create different outputs based on the order.
You could either transform s and t to float32 before applying the subtraction:

s = torch.flatten(s).float()
t = torch.flatten(t).float()

or you could index the Dataset which will normalize and cast the image tensors to float32 by applying ToTensor on them:

s = train_data[i][0]
t = train_data[j][0]
1 Like