Encounter the RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

3

Assignments to Variables are in-place operations and you’re doing a lot of them (u_i[:,j,:]). You’re using that variable in lots of other contexts and some of the functions require it to not change. This might help (I added some calls to clone):

u_i[:,j,:] = (1 - self.lumbda)*u_i[:,j,:].clone() + self.lumbda*F.relu(self.u_i_linear(tmp_x))
u_i[:,j,:] = u_i[:,j,:].clone()*comp_mask_ui.float()

alpha_i[:,j,:] = F.tanh(self.alpha_i_linear(torch.cat((u_i[:,j,:], u_s),1)))
alpha_i[:,j,:] = alpha_i[:,j,:].clone()*comp_mask.float()
25 Likes