Tensor.backward, as per documentation, frees the computation graph after the call to backward unless retain_graph is set to True. This is the exactly the behaviour I observed for the following example. x = torch.ones(1., requires_grad=True) y = torch.ones(1., requires_grad = True) w = x+y u=2*w …

Similar to this question : [image] RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time This is an edge case, since the only op you do is an add and the add does not need any buffe…

PyTorch Forums

Inconsistency in Tensor.backward

ptrblck August 1, 2019, 12:08pm 2