基於pytorch的改進的VDSR（基於FSRCNN的）
阿新 • • 發佈：2018-11-30
本博文為本人對FSRCNN+residual後的實驗的分析博文。不完全採用VDSR的程式碼，只對其中的residual部分做了參考。
之前的博文《學習筆記之——基於深度學習的影象超解析度重構》也介紹過VDSR，VDSR是基於SRCNN改進的，這裡做的是基於FSRCNN的VDSR。
VDSR的網路結構如下：
那麼本博文其實就是把這個網路結構中的SR部分由SRCNN改為FSRCNN
基於pytorch的VDSR連結（https://github.com/twtygqyy/pytorch-vdsr）
paper（https://arxiv.org/pdf/1511.04587.pdf）
下面給出修改後的程式碼：
python train.py -opt options/train/train_sr.json
#######################################################################################################3 #FSRCNN class FSRCNN(nn.Module): def __init__(self, in_nc, out_nc, nf, nb, upscale=4, norm_type='batch', act_type='relu', \ mode='NAC', res_scale=1, upsample_mode='upconv'):##play attention the upscales super(FSRCNN,self).__init__() #Feature extractionn self.conv1=nn.Conv2d(in_channels=in_nc,out_channels=nf,kernel_size=5,stride=1,padding=2)#nf=56.add padding ,make the data alignment self.prelu1=nn.PReLU() #Shrinking self.conv2=nn.Conv2d(in_channels=nf,out_channels=12,kernel_size=1,stride=1,padding=0) self.prelu2 = nn.PReLU() # Non-linear Mapping self.conv3=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu3 = nn.PReLU() self.conv4=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu4 = nn.PReLU() self.conv5=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu5 = nn.PReLU() self.conv6=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu6 = nn.PReLU() # Expanding self.conv7=nn.Conv2d(in_channels=12,out_channels=nf,kernel_size=1,stride=1,padding=0) self.prelu7 = nn.PReLU() # Deconvolution self.last_part= nn.ConvTranspose2d(in_channels=nf,out_channels=in_nc,kernel_size=9,stride=upscale, padding=4, output_padding=1) #for the residual self.DECO_part= nn.ConvTranspose2d(in_channels=in_nc,out_channels=in_nc,kernel_size=9,stride=upscale, padding=4, output_padding=1) def forward(self, x):# residual=self.DECO_part(x)########### out = self.prelu1(self.conv1(x)) out = self.prelu2(self.conv2(out)) out = self.prelu3(self.conv3(out)) out = self.prelu4(self.conv4(out)) out = self.prelu5(self.conv5(out)) out = self.prelu6(self.conv6(out)) out = self.prelu7(self.conv7(out)) out = self.last_part(out) out = torch.add(out,residual)#################### return out ##########################################################################################################
結果如下：
執行得特別得慢。。。。。
結果對比：
不採用反捲積，改為採用bicubic，程式碼修改如下：
#######################################################################################################3 #FSRCNN class FSRCNN(nn.Module): def __init__(self, in_nc, out_nc, nf, nb, upscale=4, norm_type='batch', act_type='relu', \ mode='NAC', res_scale=1, upsample_mode='upconv'):##play attention the upscales super(FSRCNN,self).__init__() #Feature extractionn self.conv1=nn.Conv2d(in_channels=in_nc,out_channels=nf,kernel_size=5,stride=1,padding=2)#nf=56.add padding ,make the data alignment self.prelu1=nn.PReLU() #Shrinking self.conv2=nn.Conv2d(in_channels=nf,out_channels=12,kernel_size=1,stride=1,padding=0) self.prelu2 = nn.PReLU() # Non-linear Mapping self.conv3=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu3 = nn.PReLU() self.conv4=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu4 = nn.PReLU() self.conv5=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu5 = nn.PReLU() self.conv6=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1) self.prelu6 = nn.PReLU() # Expanding self.conv7=nn.Conv2d(in_channels=12,out_channels=nf,kernel_size=1,stride=1,padding=0) self.prelu7 = nn.PReLU() # Deconvolution self.last_part= nn.ConvTranspose2d(in_channels=nf,out_channels=in_nc,kernel_size=9,stride=upscale, padding=4, output_padding=1) def forward(self, x):# residual=x m = nn.Upsample(scale_factor=2) residual=m(residual) #print(residual.size()) #exit() out = self.prelu1(self.conv1(x)) out = self.prelu2(self.conv2(out)) out = self.prelu3(self.conv3(out)) out = self.prelu4(self.conv4(out)) out = self.prelu5(self.conv5(out)) out = self.prelu6(self.conv6(out)) out = self.prelu7(self.conv7(out)) out = self.last_part(out) out=torch.add(out,residual)################### return out ##########################################################################################################
網路沒有辦法收斂。。。。我也不知道什麼原因了。。。。。感覺就是採用了pytorch自帶的函式這樣插值就會這樣。。。。。那還是採用反捲積來實驗resudual把
再試試程式碼如下：
#######################################################################################################3
#FSRCNN
class FSRCNN(nn.Module):
def __init__(self, in_nc, out_nc, nf, nb, upscale=4, norm_type='batch', act_type='relu', \
mode='NAC', res_scale=1, upsample_mode='upconv'):##play attention the upscales
super(FSRCNN,self).__init__()
#Feature extractionn
self.conv1=nn.Conv2d(in_channels=in_nc,out_channels=nf,kernel_size=5,stride=1,padding=2)#nf=56.add padding ,make the data alignment
self.prelu1=nn.PReLU()
#Shrinking
self.conv2=nn.Conv2d(in_channels=nf,out_channels=12,kernel_size=1,stride=1,padding=0)
self.prelu2 = nn.PReLU()
# Non-linear Mapping
self.conv3=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu3 = nn.PReLU()
self.conv4=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu4 = nn.PReLU()
self.conv5=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu5 = nn.PReLU()
self.conv6=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu6 = nn.PReLU()
# Expanding
self.conv7=nn.Conv2d(in_channels=12,out_channels=nf,kernel_size=1,stride=1,padding=0)
self.prelu7 = nn.PReLU()
# Deconvolution
self.last_part= nn.ConvTranspose2d(in_channels=nf,out_channels=in_nc,kernel_size=9,stride=upscale, padding=4, output_padding=1)
#Upsmaple
self.m=nn.UpsamplingBilinear2d(scale_factor=2)
def forward(self, x):#
residual_x=x
residual=self.m(residual_x)
#print(residual.size())
#exit()
out = self.prelu1(self.conv1(x))
out = self.prelu2(self.conv2(out))
out = self.prelu3(self.conv3(out))
out = self.prelu4(self.conv4(out))
out = self.prelu5(self.conv5(out))
out = self.prelu6(self.conv6(out))
out = self.prelu7(self.conv7(out))
out = self.last_part(out)
out=torch.add(out,residual)###################
return out
##########################################################################################################結果也是一開始不收斂，但是慢慢得訓練就好多了，可惜最終得PSNR還是比較低
再換setting
#######################################################################################################3
#FSRCNN
class FSRCNN(nn.Module):
def __init__(self, in_nc, out_nc, nf, nb, upscale=4, norm_type='batch', act_type='relu', \
mode='NAC', res_scale=1, upsample_mode='upconv'):##play attention the upscales
super(FSRCNN,self).__init__()
#Feature extractionn
self.conv1=nn.Conv2d(in_channels=in_nc,out_channels=nf,kernel_size=5,stride=1,padding=2)#nf=56.add padding ,make the data alignment
self.prelu1=nn.PReLU()
#Shrinking
self.conv2=nn.Conv2d(in_channels=nf,out_channels=12,kernel_size=1,stride=1,padding=0)
self.prelu2 = nn.PReLU()
# Non-linear Mapping
self.conv3=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu3 = nn.PReLU()
self.conv4=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu4 = nn.PReLU()
self.conv5=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu5 = nn.PReLU()
self.conv6=nn.Conv2d(in_channels=12,out_channels=12,kernel_size=3,stride=1,padding=1)
self.prelu6 = nn.PReLU()
# Expanding
self.conv7=nn.Conv2d(in_channels=12,out_channels=nf,kernel_size=1,stride=1,padding=0)
self.prelu7 = nn.PReLU()
# Deconvolution
self.last_part= nn.ConvTranspose2d(in_channels=nf,out_channels=in_nc,kernel_size=9,stride=upscale, padding=4, output_padding=1)
#Upsmaple
self.m=nn.UpsamplingNearest2d(scale_factor=2)
def forward(self, x):#
residual_x=x
residual=self.m(residual_x)
#print(residual.size())
#exit()
out = self.prelu1(self.conv1(x))
out = self.prelu2(self.conv2(out))
out = self.prelu3(self.conv3(out))
out = self.prelu4(self.conv4(out))
out = self.prelu5(self.conv5(out))
out = self.prelu6(self.conv6(out))
out = self.prelu7(self.conv7(out))
out = self.last_part(out)
out=torch.add(out,residual)###################
return out
##########################################################################################################
這樣得結果看似學習率一開始設定太大了~~~那試試把學習率設定低一點看看
補充
can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
關於pytorch中的上取樣https://blog.csdn.net/g11d111/article/details/82855946
class torch.nn.UpsamplingBilinear2d(size=None, scale_factor=None)[source]
