Hello,
I am following the Feature Loss codes and practice. I created a unet learner, but when I run learn.lr_find(), it gives NotImplementedError. Can anyone help?
Here are my codes:
bs,size=32,128
arch=models.resnet34
src=ImageImageList.from_folder(path_lr).split_by_rand_pct(0.1, seed=42)
def get_data(bs, size):
data=(src.label_from_func(lambda x: path_hr/x.name)
.transform(get_transforms(max_zoom=2.),size=size,tfm_y=True)
.databunch(bs=bs).normalize(imagenet_stats, do_y=True))
data.c=3
return data
data=get_data(bs, size)
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)
bass_loss=F.l1_loss
vgg_m=vgg16_bn(True).features.cuda().eval()
requires_grad(vgg_m, False)
blocks= [i-1 for i in range(len(vgg_m)) if isinstance(vgg_m[i],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.metrics_names, self.feat_losses))
return sum(self.feat_looses)
def __del__(self): self.hooks.remove()
feat_loss=FeatureLoss(vgg_m, blocks[2:5],[5,15,2])
wd=1e-3
learn=unet_learner(data, arch ,wd=0.001, loss_func=feat_loss, callback_fns=LossMetrics,
blur=True, norm_type=NormType.Weight)
