def goodfellow_backprop()

in fast_grad/goodfellow_backprop.py [0:0]

• 10 lines of code
• 2 McCabe index (conditional complexity)

def goodfellow_backprop(activations, linearGrads):
	grads = []
	for i in range(len(linearGrads)):
		G, X = linearGrads[i], activations[i]
		if len(G.shape) < 2:
			G = G.unsqueeze(1)

		G *= G.shape[0] # if the function is an average

		grads.append(torch.bmm(G.unsqueeze(2), X.unsqueeze(1)))
		grads.append(G)

	return grads