So to explain it nicely,
a = torch.randn(1, 3)
a
tensor([[ 0.6763, 0.7445, -2.2369]])
torch.max(a)
tensor(0.7445)
^ returns the maximum value.
But here,
a = torch.randn(4, 4)
a
tensor([[-1.2360, -0.2942, -0.1222, 0.8475],
[ 1.1949, -1.1127, -2.2379, -0.6702],
[ 1.5717, -0.9207, 0.1297, -1.8768],
[-0.6172, 1.0036, -0.6060, -0.2432]])
torch.max(a, 1)
(tensor([ 0.8475, 1.1949, 1.5717, 1.0036]), tensor([ 3, 0, 0, 1]))
It returns the value along with the index location of each maximum value i.e the argmax.
Why isn’t the index location returned in the first case?