I have a custom data generation pipeline which randomly samples 2 torch tensors (using torch.rand()), multiplies them and the product X is used as input to a PyTorch model. I set X.requires_grad_(False) before input to the model, to avoid any unnecessary gradient accumulation or backprop through the…

No, this does not change the answer as long as U and V are created via torch.rand without setting requires_grad=True: U = torch.rand((3, 3)) V = torch.rand((3, 3)) X = U @ V print(X.grad_fn) # None print(X.requires_grad) # False This would change if U or V are created by a differentiable operation…

Detach() vs requires_grad_(False) -- generating data

autograd

Arun_Sandy (Arun Sandy) January 17, 2024, 8:21pm 7

I have started this issue as a new topic in the below link :

Please have a look at it.