How to backprop with multiple outputs?

1

I wrote a demo:

criterion = nn.MSELoss()
x = Variable(torch.randn(1,100), requires_grad=True)
y = Variable(torch.randn(1,40))

class ToyModel(nn.Module):
    def __init__(self):
        super(ToyModel, self).__init__()
        self.linear1 = nn.Linear(100,50)
        self.linear2 = nn.Linear(50,40)
        self.linear3 = nn.Linear(100,40)

    def forward(self, x):
        out1 = self.linear1(x)
        out2 = self.linear2(out1)
        out3 = self.linear3(x)
        return out2,out3

model=ToyModel()
out2,out3 = model.forward(x)
print out3
loss1= criterion(out2,y)
loss2 = criterion(out3,y)
#print out2.grad

torch.autograd.backward(x, [grad1, grad2])

But how to get grad1 and grad2 ?
print out2.grad
just gives me 'None’
If using register_hook, how to use it in the nn.Module to fit my quest?

2 Likes
3

Why not format your post using Markdown?