Problem of grad becoming None

[InnovArul (Arul)]

Can you check the answer in the below post and try using list.append() instead of list.extend()?

Torch.autograd.grad got None gradients for cascaded model

tl: dr; use append() instead of extend(). Long story: The reason for this behavior is due to how extend() works. extend() iterates over the given batch variable and adds the rows one by one to x_list. By doing this, extend() creates its non-leaf nodes, which are unrelated to the computation graphs involving model1, model2. Using append() leaves batch variable untouched. [image] You can find an explanation about leaf variables from @albanD here: