How to calculate gradient of the upper part of the network

I have a simple network and the grad of the final FC layer
How can I calculate the rest grad

This tutorial might be a good starter as it introduces you to the general neural network training.

For example, I have a simple network like:
conv→conv→relu→linear
I only have the gradient of the linear layer.
I don’t have access to the loss or something like smashed data in split learning.
How can I calculate the gradient of the two conv layers or where should I use backward ?

Assuming you have the output gradient of your linear layer, something like this would work:

out = model(input) # linear output
out.backward(gradient=output_gradient)

So does it mean I still need both the output and the gradient of one layer to backward