inp = torch.tensor([[1,1,1]], dtype=torch.float)
i = torch.tensor([[1]], dtype=torch.long).view(-1, 1)
outp = self.eval_net(inp).gather(1, i)
self.optimizer.zero_grad()
loss = F.smooth_l1_loss(q_eval, 0*q_eval)
loss.backward()
so how the backward work if(eval_net) has multiple outputs ?
class Net(nn.Module):
def init(self):
super(Net, self).init()
self.fc = nn.Linear(3, 1)
self.a_head = nn.Linear(1, 2) #in this case two outputs
