Calculating accuracy of the current minibatch?

Does the following not work:

def calc_accuracy(mdl,X,Y):
    # TODO: why can't we call .data.numpy() for train_acc as a whole?
    max_vals, max_indices = torch.max(mdl(X),1)
    train_acc = (max_indices == Y).sum().data.numpy()/max_indices.size()[0]
    return train_acc

??