How does optimizer work when there are 3 backwards(real, fake, penalty)?

[wook3024]

I thought I should write like
"D_cost = D_fake - D_real + gradient_penalty
D_cost.backward()"
but I don't know why you use backward like that.

wgan-gp/gan_cifar10.py

Lines 203 to 226 in ae47a18

	D_real = netD(real_data_v)
	D_real = D_real.mean()
	D_real.backward(mone)
	# train with fake
	noise = torch.randn(BATCH_SIZE, 128)
	if use_cuda:
	noise = noise.cuda(gpu)
	noisev = autograd.Variable(noise, volatile=True) # totally freeze netG
	fake = autograd.Variable(netG(noisev).data)
	inputv = fake
	D_fake = netD(inputv)
	D_fake = D_fake.mean()
	D_fake.backward(one)
	# train with gradient penalty
	gradient_penalty = calc_gradient_penalty(netD, real_data_v.data, fake.data)
	gradient_penalty.backward()
	# print "gradien_penalty: ", gradient_penalty
	D_cost = D_fake - D_real + gradient_penalty
	Wasserstein_D = D_real - D_fake
	optimizerD.step()