Vide Restoration using Deep Learning

create_network.py

# adapted from: https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson7-superres.ipynb

t = data.valid_ds[0][1].data
t = torch.stack([t,t])

def gram_matrix(x):
	n,c,h,w = x.size()
	x = x.view(n, c, -1)
	return (x @ x.transpose(1,2))/(c*h*w)

base_loss = F.l1_loss

vgg_m = vgg16_bn(True).features.cuda().eval()
requires_grad(vgg_m, False)

blocks = [i-1 for i,o in enumerate(children(vgg_m)) if isinstance(o,nn.MaxPool2d)]
blocks, [vgg_m[i] for i in blocks]

class FeatureLoss(nn.Module):
	def __init__(self, m_feat, layer_ids, layer_wgts):
		super().__init__()
		self.m_feat = m_feat
		self.loss_features = [self.m_feat[i] for i in layer_ids]
		self.hooks = hook_outputs(self.loss_features, detach=False)
		self.wgts = layer_wgts
		self.metric_names = ['pixel',] + [f'feat_{i}' for i in range(len(layer_ids))
			  ] + [f'gram_{i}' for i in range(len(layer_ids))]

	def make_features(self, x, clone=False):
		self.m_feat(x)
		return [(o.clone() if clone else o) for o in self.hooks.stored]
	
	def forward(self, input, target):
		out_feat = self.make_features(target, clone=True)
		in_feat = self.make_features(input)
		self.feat_losses = [base_loss(input,target)]
		self.feat_losses += [base_loss(f_in, f_out)*w
							 for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)]
		self.feat_losses += [base_loss(gram_matrix(f_in), gram_matrix(f_out))*w**2 * 5e3
							 for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)]
		self.metrics = dict(zip(self.metric_names, self.feat_losses))
		return sum(self.feat_losses)
	
	def __del__(self): self.hooks.remove()

feat_loss = FeatureLoss(vgg_m, blocks[2:5], [5,15,2])