What does fs[:, i, :] = f do?

#1

Hello, I am trying action recognition. If I understand correctly the code f = f.view(f.size(0), -1) flattens the tensor but for fs[:, i, :] = f, I can’t seem to guess what it is doing there.

  def forward(self, inputs, hidden=None, steps=0):
        length = len(inputs)
        fs = torch.zeros(inputs[0].size(0), length, self.rnn.input_size).cuda()

        for i in range(length):
            f = inputs[i]
            f = f.view(f.size(0), -1)
            f = self.fc_pre(f)
            fs[:, i, :] = f

Thank you in advance

#2

fs[:, i, :] = f assigns the tensor f in the shape [fs.size(0), fs.size(2)] to each “row” in fs.
Here is a small example where f is containing increasing values for the sake of simplicity:

fs = torch.randn(2, 3, 4)
f = torch.randn(2, 4)

for i in range(fs.size(1)):
    f = torch.ones(fs.size(0), fs.size(2)) * i
    print(f)
    fs[:, i, :] = f

# tensor([[0., 0., 0., 0.],
#         [0., 0., 0., 0.]])
# tensor([[1., 1., 1., 1.],
#         [1., 1., 1., 1.]])
# tensor([[2., 2., 2., 2.],
#         [2., 2., 2., 2.]])
    
print(fs)
# tensor([[[0., 0., 0., 0.],
#          [1., 1., 1., 1.],
#          [2., 2., 2., 2.]],

#         [[0., 0., 0., 0.],
#          [1., 1., 1., 1.],
#          [2., 2., 2., 2.]]])
1 Like
#3

Thank you for the explanation @ptrblck :pray: