add archs folder

archs/__init__.py

@@ -0,0 +1,4 @@
+from .nafnet_utils.arch_model import NAFNet
+from .network import Network
+
+__all__ = ['NAFNet','Network']

archs/arch_util.py

@@ -0,0 +1,229 @@
+import torch
+import torch.nn as nn
+import torch.nn.init as init
+import torch.nn.functional as F
+
+try:
+    from .nafnet_utils.arch_util import LayerNorm2d
+    from .nafnet_utils.arch_model import SimpleGate
+except:
+    from nafnet_utils.arch_util import LayerNorm2d
+    from nafnet_utils.arch_model import SimpleGate
+
+'''
+https://github.com/wangchx67/FourLLIE.git
+'''
+
+def initialize_weights(net_l, scale=1):
+    if not isinstance(net_l, list):
+        net_l = [net_l]
+    for net in net_l:
+        for m in net.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
+                m.weight.data *= scale  # for residual block
+                if m.bias is not None:
+                    m.bias.data.zero_()
+            elif isinstance(m, nn.Linear):
+                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                init.constant_(m.weight, 1)
+                init.constant_(m.bias.data, 0.0)
+
+
+def make_layer(block, n_layers):
+    layers = []
+    for _ in range(n_layers):
+        layers.append(block())
+    return nn.Sequential(*layers)
+
+
+class ResidualBlock_noBN(nn.Module):
+    '''Residual block w/o BN
+    ---Conv-ReLU-Conv-+-
+     |________________|
+    '''
+
+    def __init__(self, nf=64):
+        super(ResidualBlock_noBN, self).__init__()
+        self.conv1 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
+        self.conv2 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
+
+        # initialization
+        initialize_weights([self.conv1, self.conv2], 0.1)
+
+    def forward(self, x):
+        identity = x
+        out = F.relu(self.conv1(x), inplace=True)
+        out = self.conv2(out)
+        return identity + out
+
+class SpaBlock(nn.Module):
+    def __init__(self, nc):
+        super(SpaBlock, self).__init__()
+        self.block = nn.Sequential(
+            nn.Conv2d(nc,nc,3,1,1),
+            nn.LeakyReLU(0.1,inplace=True),
+            nn.Conv2d(nc, nc, 3, 1, 1),
+            nn.LeakyReLU(0.1, inplace=True))
+
+    def forward(self, x):
+        return x+self.block(x)
+
+class FreBlock(nn.Module):
+    def __init__(self, nc):
+        super(FreBlock, self).__init__()
+        self.fpre = nn.Conv2d(nc, nc, 1, 1, 0)
+        self.process1 = nn.Sequential(
+            nn.Conv2d(nc, nc, 1, 1, 0),
+            nn.LeakyReLU(0.1, inplace=True),
+            nn.Conv2d(nc, nc, 1, 1, 0))
+        self.process2 = nn.Sequential(
+            nn.Conv2d(nc, nc, 1, 1, 0),
+            nn.LeakyReLU(0.1, inplace=True),
+            nn.Conv2d(nc, nc, 1, 1, 0))
+
+    def forward(self, x):
+        _, _, H, W = x.shape
+        x_freq = torch.fft.rfft2(self.fpre(x), norm='backward')
+        mag = torch.abs(x_freq)
+        pha = torch.angle(x_freq)
+        mag = self.process1(mag)
+        pha = self.process2(pha)
+        real = mag * torch.cos(pha)
+        imag = mag * torch.sin(pha)
+        x_out = torch.complex(real, imag)
+        x_out = torch.fft.irfft2(x_out, s=(H, W), norm='backward')
+
+        return x_out+x
+
+class ProcessBlock(nn.Module):
+    def __init__(self, in_nc, spatial = True):
+        super(ProcessBlock,self).__init__()
+        self.spatial = spatial
+        self.spatial_process = SpaBlock(in_nc) if spatial else nn.Identity()
+        self.frequency_process = FreBlock(in_nc)
+        self.cat = nn.Conv2d(2*in_nc,in_nc,1,1,0) if spatial else nn.Conv2d(in_nc,in_nc,1,1,0)
+
+    def forward(self, x):
+        xori = x
+        x_freq = self.frequency_process(x)
+        x_spatial = self.spatial_process(x)
+        xcat = torch.cat([x_spatial,x_freq],1)
+        x_out = self.cat(xcat) if self.spatial else self.cat(x_freq)
+
+        return x_out+xori
+
+class Attention_Light(nn.Module):
+    
+    def __init__(self, img_channels = 3, width = 16, spatial = False):
+        super(Attention_Light, self).__init__()
+        self.block = nn.Sequential(
+                nn.Conv2d(in_channels = img_channels, out_channels = width//2, kernel_size = 1, padding = 0, stride = 1, groups = 1, bias = True),
+                ProcessBlock(in_nc = width //2, spatial = spatial),
+                nn.Conv2d(in_channels = width//2, out_channels = width, kernel_size = 1, padding = 0, stride = 1, groups = 1, bias = True),
+                ProcessBlock(in_nc = width, spatial = spatial),
+                nn.Conv2d(in_channels = width, out_channels = width, kernel_size = 1, padding = 0, stride = 1, groups = 1, bias = True),
+                ProcessBlock(in_nc=width, spatial = spatial),
+                nn.Sigmoid()
+                    )
+    def forward(self, input):
+        return self.block(input)
+
+class Branch(nn.Module):
+    '''
+    Branch that lasts lonly the dilated convolutions
+    '''
+    def __init__(self, c, DW_Expand, dilation = 1, extra_depth_wise = False):
+        super().__init__()
+        self.dw_channel = DW_Expand * c 
+        self.branch = nn.Sequential(
+                       nn.Conv2d(c, c, kernel_size=3, padding=1, stride=1, groups=c, bias=True, dilation=1) if extra_depth_wise else nn.Identity(), #optional extra dw
+                       nn.Conv2d(in_channels=c, out_channels=self.dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1),
+                       nn.Conv2d(in_channels=self.dw_channel, out_channels=self.dw_channel, kernel_size=3, padding=dilation, stride=1, groups=self.dw_channel,
+                                            bias=True, dilation = dilation) # the dconv
+        )
+    def forward(self, input):
+        return self.branch(input)
+    
+class EBlock(nn.Module):
+    '''
+    Change this block using Branch
+    '''
+    
+    def __init__(self, c, DW_Expand=2, FFN_Expand=2, dilations = [1], extra_depth_wise = False):
+        super().__init__()
+        #we define the 2 branches
+        
+        self.branches = nn.ModuleList()
+        for dilation in dilations:
+            self.branches.append(Branch(c, DW_Expand, dilation = dilation, extra_depth_wise=extra_depth_wise))
+            
+        assert len(dilations) == len(self.branches)
+        self.dw_channel = DW_Expand * c 
+        self.sca = nn.Sequential(
+                       nn.AdaptiveAvgPool2d(1),
+                       nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=self.dw_channel // 2, kernel_size=1, padding=0, stride=1,
+                       groups=1, bias=True, dilation = 1),  
+        )
+        self.sg1 = SimpleGate()
+        self.sg2 = SimpleGate()
+        self.conv3 = nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1)
+        ffn_channel = FFN_Expand * c
+        self.conv4 = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(in_channels=ffn_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+
+        self.norm1 = LayerNorm2d(c)
+        self.norm2 = LayerNorm2d(c)
+
+        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+
+    def forward(self, inp):
+
+        y = inp
+        x = self.norm1(inp)
+        z = 0
+        for branch in self.branches:
+            z += branch(x)
+        
+        z = self.sg1(z)
+        x = self.sca(z) * z
+        x = self.conv3(x)
+        y = inp + self.beta * x
+        #second step
+        x = self.conv4(self.norm2(y)) # size [B, 2*C, H, W]
+        x = self.sg2(x)  # size [B, C, H, W]
+        x = self.conv5(x) # size [B, C, H, W]
+
+        return y + x * self.gamma
+
+#----------------------------------------------------------------------------------------------
+if __name__ == '__main__':
+    
+    img_channel = 3
+    width = 32
+
+    enc_blks = [1, 2, 3]
+    middle_blk_num = 3
+    dec_blks = [3, 1, 1]
+    dilations = [1, 4, 9]
+    extra_depth_wise = False
+    
+    # net = NAFNet(img_channel=img_channel, width=width, middle_blk_num=middle_blk_num,
+    #                   enc_blk_nums=enc_blks, dec_blk_nums=dec_blks)
+    net  = EBlock(c = img_channel, 
+                            dilations = dilations,
+                            extra_depth_wise=extra_depth_wise)
+
+    inp_shape = (3, 256, 256)
+
+    from ptflops import get_model_complexity_info
+
+    macs, params = get_model_complexity_info(net, inp_shape, verbose=False, print_per_layer_stat=True)
+
+
+    print(macs, params)

archs/arch_util_freq.py

@@ -0,0 +1,149 @@
+import torch
+import torch.nn as nn
+import torch.nn.init as init
+import torch.nn.functional as F
+
+try:
+    from .nafnet_utils.arch_util import LayerNorm2d
+    from .nafnet_utils.arch_model import SimpleGate
+except:
+    from nafnet_utils.arch_util import LayerNorm2d
+    from nafnet_utils.arch_model import SimpleGate
+
+'''
+https://github.com/wangchx67/FourLLIE.git
+'''
+
+def initialize_weights(net_l, scale=1):
+    if not isinstance(net_l, list):
+        net_l = [net_l]
+    for net in net_l:
+        for m in net.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
+                m.weight.data *= scale  # for residual block
+                if m.bias is not None:
+                    m.bias.data.zero_()
+            elif isinstance(m, nn.Linear):
+                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                init.constant_(m.weight, 1)
+                init.constant_(m.bias.data, 0.0)
+
+class FreNAFBlock(nn.Module):
+    
+    def __init__(self, nc, expand = 2):
+        super(FreNAFBlock, self).__init__()
+        self.process1 = nn.Sequential(
+            nn.Conv2d(nc, expand * nc, 1, 1, 0),
+            nn.LeakyReLU(0.1, inplace=True),
+            nn.Conv2d(expand * nc, nc, 1, 1, 0))
+
+    def forward(self, x):
+        _, _, H, W = x.shape
+        x_freq = torch.fft.rfft2(x, norm='backward')
+        mag = torch.abs(x_freq)
+        pha = torch.angle(x_freq)
+        mag = self.process1(mag)
+        real = mag * torch.cos(pha)
+        imag = mag * torch.sin(pha)
+        x_out = torch.complex(real, imag)
+        x_out = torch.fft.irfft2(x_out, s=(H, W), norm='backward')
+        return x_out
+
+# ------------------------------------------------------------------------------------------------
+
+class Branch(nn.Module):
+    '''
+    Branch that lasts lonly the dilated convolutions
+    '''
+    def __init__(self, c, DW_Expand, dilation = 1, extra_depth_wise = False):
+        super().__init__()
+        self.dw_channel = DW_Expand * c 
+        self.branch = nn.Sequential(
+                       nn.Conv2d(c, c, kernel_size=3, padding=1, stride=1, groups=c, bias=True, dilation=1) if extra_depth_wise else nn.Identity(), #optional extra dw
+                       nn.Conv2d(in_channels=c, out_channels=self.dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1),
+                       nn.Conv2d(in_channels=self.dw_channel, out_channels=self.dw_channel, kernel_size=3, padding=dilation, stride=1, groups=self.dw_channel,
+                                            bias=True, dilation = dilation) # the dconv
+        )
+    def forward(self, input):
+        return self.branch(input)
+    
+class EBlock_freq(nn.Module):
+    '''
+    Change this block using Branch
+    '''
+    
+    def __init__(self, c, DW_Expand=2, dilations = [1], extra_depth_wise = False):
+        super().__init__()
+        #we define the 2 branches
+        
+        self.branches = nn.ModuleList()
+        for dilation in dilations:
+            self.branches.append(Branch(c, DW_Expand, dilation = dilation, extra_depth_wise=extra_depth_wise))
+            
+        assert len(dilations) == len(self.branches)
+        self.dw_channel = DW_Expand * c 
+        self.sca = nn.Sequential(
+                       nn.AdaptiveAvgPool2d(1),
+                       nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=self.dw_channel // 2, kernel_size=1, padding=0, stride=1,
+                       groups=1, bias=True, dilation = 1),  
+        )
+        self.sg1 = SimpleGate()
+        self.conv3 = nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1)
+        # second step
+
+        self.norm1 = LayerNorm2d(c)
+        self.norm2 = LayerNorm2d(c)
+        self.freq = FreNAFBlock(nc = c, expand=2)
+        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+
+    def forward(self, inp):
+
+        y = inp
+        x = self.norm1(inp)
+        z = 0
+        for branch in self.branches:
+            z += branch(x)
+        
+        z = self.sg1(z)
+        x = self.sca(z) * z
+        x = self.conv3(x)
+        y = inp + self.beta * x
+        #second step
+        x_step2 = self.norm2(y) # size [B, 2*C, H, W]
+        x_freq = self.freq(x_step2) # size [B, C, H, W]
+        x = y * x_freq 
+        
+        return y + x * self.gamma
+
+#----------------------------------------------------------------------------------------------
+if __name__ == '__main__':
+    
+    img_channel = 128
+    width = 32
+
+    enc_blks = [1, 2, 3]
+    middle_blk_num = 3
+    dec_blks = [3, 1, 1]
+    dilations = [1, 4, 9]
+    extra_depth_wise = True
+    
+    # net = NAFNet(img_channel=img_channel, width=width, middle_blk_num=middle_blk_num,
+    #                   enc_blk_nums=enc_blks, dec_blk_nums=dec_blks)
+    net  = EBlock(c = img_channel, 
+                            dilations = dilations,
+                            extra_depth_wise=extra_depth_wise)
+
+    inp_shape = (128, 32, 32)
+
+    from ptflops import get_model_complexity_info
+
+    macs, params = get_model_complexity_info(net, inp_shape, verbose=False, print_per_layer_stat=False)
+
+
+    print(macs, params)

archs/nafnet_utils/arch_model.py

@@ -0,0 +1,301 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+try:
+    from .arch_util import LayerNorm2d
+    from .local_arch import Local_Base
+except:
+    from arch_util import LayerNorm2d
+    from local_arch import Local_Base
+
+
+class SimpleGate(nn.Module):
+    def forward(self, x):
+        x1, x2 = x.chunk(2, dim=1)
+        return x1 * x2
+
+class NAFBlock(nn.Module):
+    def __init__(self, c, DW_Expand=2, FFN_Expand=2, drop_out_rate=0.):
+        super().__init__()
+        dw_channel = c * DW_Expand
+        self.conv1 = nn.Conv2d(in_channels=c, out_channels=dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv2 = nn.Conv2d(in_channels=dw_channel, out_channels=dw_channel, kernel_size=3, padding=1, stride=1, groups=dw_channel,
+                               bias=True) # the dconv
+        self.conv3 = nn.Conv2d(in_channels=dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        
+        # Simplified Channel Attention
+        self.sca = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(in_channels=dw_channel // 2, out_channels=dw_channel // 2, kernel_size=1, padding=0, stride=1,
+                      groups=1, bias=True),
+        )
+
+        # SimpleGate
+        self.sg = SimpleGate()
+
+        ffn_channel = FFN_Expand * c
+        self.conv4 = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(in_channels=ffn_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+
+        self.norm1 = LayerNorm2d(c)
+        self.norm2 = LayerNorm2d(c)
+
+        self.dropout1 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()
+        self.dropout2 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()
+
+        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+
+    def forward(self, inp):
+        x = inp           # size [B, C, H, W]
+
+        x = self.norm1(x) # size [B, C, H, W]
+
+        x = self.conv1(x) # size [B, 2*C, H, W]
+        x = self.conv2(x) # size [B, 2*C, H, W]
+        x = self.sg(x)    # size [B, C, H, W]
+        x = x * self.sca(x) # size [B, C, H, W]
+        x = self.conv3(x) # size [B, C, H, W]
+
+        x = self.dropout1(x)
+
+        y = inp + x * self.beta # size [B, C, H, W]
+
+        x = self.conv4(self.norm2(y)) # size [B, 2*C, H, W]
+        x = self.sg(x)  # size [B, C, H, W]
+        x = self.conv5(x) # size [B, C, H, W]
+
+        x = self.dropout2(x)
+
+        return y + x * self.gamma
+
+
+class NAFNet(nn.Module):
+
+    def __init__(self, img_channel=3, width=16, middle_blk_num=1, enc_blk_nums=[], dec_blk_nums=[]):
+        super().__init__()
+
+        self.intro = nn.Conv2d(in_channels=img_channel, out_channels=width, kernel_size=3, padding=1, stride=1, groups=1,
+                              bias=True)
+        self.ending = nn.Conv2d(in_channels=width, out_channels=img_channel, kernel_size=3, padding=1, stride=1, groups=1,
+                              bias=True)
+
+        self.encoders = nn.ModuleList()
+        self.decoders = nn.ModuleList()
+        self.middle_blks = nn.ModuleList()
+        self.ups = nn.ModuleList()
+        self.downs = nn.ModuleList()
+
+        chan = width
+        for num in enc_blk_nums:
+            self.encoders.append(
+                nn.Sequential(
+                    *[NAFBlock(chan) for _ in range(num)]
+                )
+            )
+            self.downs.append(
+                nn.Conv2d(chan, 2*chan, 2, 2)
+            )
+            chan = chan * 2
+
+        self.middle_blks = \
+            nn.Sequential(
+                *[NAFBlock(chan) for _ in range(middle_blk_num)]
+            )
+
+        for num in dec_blk_nums:
+            self.ups.append(
+                nn.Sequential(
+                    nn.Conv2d(chan, chan * 2, 1, bias=False),
+                    nn.PixelShuffle(2)
+                )
+            )
+            chan = chan // 2
+            self.decoders.append(
+                nn.Sequential(
+                    *[NAFBlock(chan) for _ in range(num)]
+                )
+            )
+
+        self.padder_size = 2 ** len(self.encoders)
+
+    def forward(self, inp):
+        B, C, H, W = inp.shape
+        inp = self.check_image_size(inp)
+
+        x = self.intro(inp)
+
+        encs = []
+
+        for encoder, down in zip(self.encoders, self.downs):
+            x = encoder(x)
+            encs.append(x)
+            x = down(x)
+
+        x = self.middle_blks(x)
+
+        for decoder, up, enc_skip in zip(self.decoders, self.ups, encs[::-1]):
+            x = up(x)
+            x = x + enc_skip
+            x = decoder(x)
+
+        x = self.ending(x)
+        x = x + inp
+
+        return x[:, :, :H, :W]
+
+    def check_image_size(self, x):
+        _, _, h, w = x.size()
+        mod_pad_h = (self.padder_size - h % self.padder_size) % self.padder_size
+        mod_pad_w = (self.padder_size - w % self.padder_size) % self.padder_size
+        x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), value = 0)
+        return x
+
+
+class NAFNetLocal(Local_Base, NAFNet):
+    def __init__(self, *args, train_size=(1, 3, 256, 256), fast_imp=False, **kwargs):
+        Local_Base.__init__(self)
+        NAFNet.__init__(self, *args, **kwargs)
+
+        N, C, H, W = train_size
+        base_size = (int(H * 1.5), int(W * 1.5))
+
+        self.eval()
+        with torch.no_grad():
+            self.convert(base_size=base_size, train_size=train_size, fast_imp=fast_imp)
+
+class FreBlock(nn.Module):
+    def __init__(self, nc):
+        super(FreBlock, self).__init__()
+        self.fpre = nn.Conv2d(nc, nc, 1, 1, 0)
+        self.process1 = nn.Sequential(
+            nn.Conv2d(nc, nc, 1, 1, 0),
+            nn.LeakyReLU(0.1, inplace=True),
+            nn.Conv2d(nc, nc, 1, 1, 0))
+        self.process2 = nn.Sequential(
+            nn.Conv2d(nc, nc, 1, 1, 0),
+            nn.LeakyReLU(0.1, inplace=True),
+            nn.Conv2d(nc, nc, 1, 1, 0))
+
+    def forward(self, x):
+        _, _, H, W = x.shape
+        x_freq = torch.fft.rfft2(self.fpre(x), norm='backward')
+        mag = torch.abs(x_freq)
+        pha = torch.angle(x_freq)
+        mag = self.process1(mag)
+        pha = self.process2(pha)
+        real = mag * torch.cos(pha)
+        imag = mag * torch.sin(pha)
+        x_out = torch.complex(real, imag)
+        x_out = torch.fft.irfft2(x_out, s=(H, W), norm='backward')
+
+        return x_out+x
+
+# class FPA(nn.Module):
+    
+#     def __init__(self,nc):
+#         super(FPA, self).__init__()
+#         self.process_mag = nn.Sequential(
+#             nn.Conv2d(nc, nc, 1, 1, 0),
+#             nn.LeakyReLU(0.1, inplace=True),
+#             nn.Conv2d(nc, nc, 1, 1, 0),
+#             nn.LeakyReLU(0.1, inplace=True),
+#             nn.Conv2d(nc, nc, 1, 1, 0))
+#         self.process_pha = nn.Sequential(
+#             nn.Conv2d(nc, nc, 1, 1, 0),
+#             nn.LeakyReLU(0.1, inplace=True),
+#             nn.Conv2d(nc, nc, 1, 1, 0),
+#             nn.LeakyReLU(0.1, inplace=True),
+#             nn.Conv2d(nc, nc, 1, 1, 0))
+        
+#     def forward(self, input):
+#         _, _, H, W = input.shape
+#         x_freq = torch.fft.rfft2(input, norm='backward')
+#         mag = torch.abs(x_freq)
+#         pha = torch.angle(x_freq)
+#         mag = mag + self.process_mag(mag)
+#         pha = pha + self.process_pha(pha)
+#         real = mag * torch.cos(pha)
+#         imag = mag * torch.sin(pha)
+#         x_out = torch.complex(real, imag)
+#         x_out = torch.fft.irfft2(x_out, s=(H, W), norm='backward')
+#         return x_out
+        
+
+# class FBlock(nn.Module):
+    
+#     def __init__(self, c, DW_Expand=2, FFN_Expand=2, dilations = [1], extra_depth_wise = False):
+#         super(FBlock, self).__init__()
+        
+#         self.branches = nn.ModuleList()
+#         for dilation in dilations:
+#             self.branches.append(Branch_v2(c, DW_Expand, dilation = dilation, extra_depth_wise=extra_depth_wise))
+
+#         assert len(dilations) == len(self.branches)
+#         self.dw_channel = DW_Expand * c 
+#         self.sca = nn.Sequential(
+#                        nn.AdaptiveAvgPool2d(1),
+#                        nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=self.dw_channel // 2, kernel_size=1, padding=0, stride=1,
+#                        groups=1, bias=True, dilation = 1),  
+#         )
+#         self.sg1 = SimpleGate()
+#         self.conv3 = nn.Conv2d(in_channels=self.dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1)
+
+
+
+#         self.norm1 = LayerNorm2d(c)
+#         self.norm2 = LayerNorm2d(c)
+        
+#         ffn_channel = FFN_Expand * c
+#         self.conv_fpr_intro = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1)
+#         self.fpa = FPA(nc = ffn_channel)
+#         self.conv_fpr_out = nn.Conv2d(in_channels=ffn_channel, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True, dilation = 1)
+        
+#         self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+#         self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
+
+    def forward(self, inp):
+
+        y = inp
+        x = self.norm1(inp)
+        z=0
+        for branch in self.branches:
+            z += branch(x)
+        
+        z = self.sg1(z)
+        x = self.sca(z) * z
+        x = self.conv3(x)
+        y = inp + self.beta * x
+        #Frequency pixel residue
+        x = self.conv_fpr_intro(self.norm2(y)) # size [B, C, H, W]
+        x = self.fpa(x)  # size [B, C, H, W]
+        x = self.conv_fpr_out(x)
+
+        return y + x * self.gamma
+
+if __name__ == '__main__':
+    
+    img_channel = 3
+    width = 32
+
+    enc_blks = [1, 2, 3]
+    middle_blk_num = 3
+    dec_blks = [3, 1, 1]
+    dilations = [1, 4, 9]
+    extra_depth_wise = False
+    
+    # net = NAFNet(img_channel=img_channel, width=width, middle_blk_num=middle_blk_num,
+    #                   enc_blk_nums=enc_blks, dec_blk_nums=dec_blks)
+    net  = EBlock_v2(c = img_channel, 
+                            dilations = dilations,
+                            extra_depth_wise=extra_depth_wise)
+
+    inp_shape = (3, 256, 256)
+
+    from ptflops import get_model_complexity_info
+
+    macs, params = get_model_complexity_info(net, inp_shape, verbose=False, print_per_layer_stat=True)
+
+
+    print(macs, params)

archs/nafnet_utils/arch_util.py

@@ -0,0 +1,343 @@
+import math
+import torch
+from torch import nn as nn
+from torch.nn import functional as F
+from torch.nn import init as init
+from torch.nn.modules.batchnorm import _BatchNorm
+
+
+# try:
+#     from basicsr.models.ops.dcn import (ModulatedDeformConvPack,
+#                                         modulated_deform_conv)
+# except ImportError:
+#     # print('Cannot import dcn. Ignore this warning if dcn is not used. '
+#     #       'Otherwise install BasicSR with compiling dcn.')
+#
+
+@torch.no_grad()
+def default_init_weights(module_list, scale=1, bias_fill=0, **kwargs):
+    """Initialize network weights.
+
+    Args:
+        module_list (list[nn.Module] | nn.Module): Modules to be initialized.
+        scale (float): Scale initialized weights, especially for residual
+            blocks. Default: 1.
+        bias_fill (float): The value to fill bias. Default: 0
+        kwargs (dict): Other arguments for initialization function.
+    """
+    if not isinstance(module_list, list):
+        module_list = [module_list]
+    for module in module_list:
+        for m in module.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, **kwargs)
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+            elif isinstance(m, nn.Linear):
+                init.kaiming_normal_(m.weight, **kwargs)
+                m.weight.data *= scale
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+            elif isinstance(m, _BatchNorm):
+                init.constant_(m.weight, 1)
+                if m.bias is not None:
+                    m.bias.data.fill_(bias_fill)
+
+
+def make_layer(basic_block, num_basic_block, **kwarg):
+    """Make layers by stacking the same blocks.
+
+    Args:
+        basic_block (nn.module): nn.module class for basic block.
+        num_basic_block (int): number of blocks.
+
+    Returns:
+        nn.Sequential: Stacked blocks in nn.Sequential.
+    """
+    layers = []
+    for _ in range(num_basic_block):
+        layers.append(basic_block(**kwarg))
+    return nn.Sequential(*layers)
+
+
+class ResidualBlockNoBN(nn.Module):
+    """Residual block without BN.
+
+    It has a style of:
+        ---Conv-ReLU-Conv-+-
+         |________________|
+
+    Args:
+        num_feat (int): Channel number of intermediate features.
+            Default: 64.
+        res_scale (float): Residual scale. Default: 1.
+        pytorch_init (bool): If set to True, use pytorch default init,
+            otherwise, use default_init_weights. Default: False.
+    """
+
+    def __init__(self, num_feat=64, res_scale=1, pytorch_init=False):
+        super(ResidualBlockNoBN, self).__init__()
+        self.res_scale = res_scale
+        self.conv1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
+        self.conv2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
+        self.relu = nn.ReLU(inplace=True)
+
+        if not pytorch_init:
+            default_init_weights([self.conv1, self.conv2], 0.1)
+
+    def forward(self, x):
+        identity = x
+        out = self.conv2(self.relu(self.conv1(x)))
+        return identity + out * self.res_scale
+
+
+class Upsample(nn.Sequential):
+    """Upsample module.
+
+    Args:
+        scale (int): Scale factor. Supported scales: 2^n and 3.
+        num_feat (int): Channel number of intermediate features.
+    """
+
+    def __init__(self, scale, num_feat):
+        m = []
+        if (scale & (scale - 1)) == 0:  # scale = 2^n
+            for _ in range(int(math.log(scale, 2))):
+                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
+                m.append(nn.PixelShuffle(2))
+        elif scale == 3:
+            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
+            m.append(nn.PixelShuffle(3))
+        else:
+            raise ValueError(f'scale {scale} is not supported. '
+                             'Supported scales: 2^n and 3.')
+        super(Upsample, self).__init__(*m)
+
+
+def flow_warp(x,
+              flow,
+              interp_mode='bilinear',
+              padding_mode='zeros',
+              align_corners=True):
+    """Warp an image or feature map with optical flow.
+
+    Args:
+        x (Tensor): Tensor with size (n, c, h, w).
+        flow (Tensor): Tensor with size (n, h, w, 2), normal value.
+        interp_mode (str): 'nearest' or 'bilinear'. Default: 'bilinear'.
+        padding_mode (str): 'zeros' or 'border' or 'reflection'.
+            Default: 'zeros'.
+        align_corners (bool): Before pytorch 1.3, the default value is
+            align_corners=True. After pytorch 1.3, the default value is
+            align_corners=False. Here, we use the True as default.
+
+    Returns:
+        Tensor: Warped image or feature map.
+    """
+    assert x.size()[-2:] == flow.size()[1:3]
+    _, _, h, w = x.size()
+    # create mesh grid
+    grid_y, grid_x = torch.meshgrid(
+        torch.arange(0, h).type_as(x),
+        torch.arange(0, w).type_as(x))
+    grid = torch.stack((grid_x, grid_y), 2).float()  # W(x), H(y), 2
+    grid.requires_grad = False
+
+    vgrid = grid + flow
+    # scale grid to [-1,1]
+    vgrid_x = 2.0 * vgrid[:, :, :, 0] / max(w - 1, 1) - 1.0
+    vgrid_y = 2.0 * vgrid[:, :, :, 1] / max(h - 1, 1) - 1.0
+    vgrid_scaled = torch.stack((vgrid_x, vgrid_y), dim=3)
+    output = F.grid_sample(
+        x,
+        vgrid_scaled,
+        mode=interp_mode,
+        padding_mode=padding_mode,
+        align_corners=align_corners)
+
+    # TODO, what if align_corners=False
+    return output
+
+
+def resize_flow(flow,
+                size_type,
+                sizes,
+                interp_mode='bilinear',
+                align_corners=False):
+    """Resize a flow according to ratio or shape.
+
+    Args:
+        flow (Tensor): Precomputed flow. shape [N, 2, H, W].
+        size_type (str): 'ratio' or 'shape'.
+        sizes (list[int | float]): the ratio for resizing or the final output
+            shape.
+            1) The order of ratio should be [ratio_h, ratio_w]. For
+            downsampling, the ratio should be smaller than 1.0 (i.e., ratio
+            < 1.0). For upsampling, the ratio should be larger than 1.0 (i.e.,
+            ratio > 1.0).
+            2) The order of output_size should be [out_h, out_w].
+        interp_mode (str): The mode of interpolation for resizing.
+            Default: 'bilinear'.
+        align_corners (bool): Whether align corners. Default: False.
+
+    Returns:
+        Tensor: Resized flow.
+    """
+    _, _, flow_h, flow_w = flow.size()
+    if size_type == 'ratio':
+        output_h, output_w = int(flow_h * sizes[0]), int(flow_w * sizes[1])
+    elif size_type == 'shape':
+        output_h, output_w = sizes[0], sizes[1]
+    else:
+        raise ValueError(
+            f'Size type should be ratio or shape, but got type {size_type}.')
+
+    input_flow = flow.clone()
+    ratio_h = output_h / flow_h
+    ratio_w = output_w / flow_w
+    input_flow[:, 0, :, :] *= ratio_w
+    input_flow[:, 1, :, :] *= ratio_h
+    resized_flow = F.interpolate(
+        input=input_flow,
+        size=(output_h, output_w),
+        mode=interp_mode,
+        align_corners=align_corners)
+    return resized_flow
+
+
+# TODO: may write a cpp file
+def pixel_unshuffle(x, scale):
+    """ Pixel unshuffle.
+
+    Args:
+        x (Tensor): Input feature with shape (b, c, hh, hw).
+        scale (int): Downsample ratio.
+
+    Returns:
+        Tensor: the pixel unshuffled feature.
+    """
+    b, c, hh, hw = x.size()
+    out_channel = c * (scale**2)
+    assert hh % scale == 0 and hw % scale == 0
+    h = hh // scale
+    w = hw // scale
+    x_view = x.view(b, c, h, scale, w, scale)
+    return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)
+
+
+# class DCNv2Pack(ModulatedDeformConvPack):
+#     """Modulated deformable conv for deformable alignment.
+#
+#     Different from the official DCNv2Pack, which generates offsets and masks
+#     from the preceding features, this DCNv2Pack takes another different
+#     features to generate offsets and masks.
+#
+#     Ref:
+#         Delving Deep into Deformable Alignment in Video Super-Resolution.
+#     """
+#
+#     def forward(self, x, feat):
+#         out = self.conv_offset(feat)
+#         o1, o2, mask = torch.chunk(out, 3, dim=1)
+#         offset = torch.cat((o1, o2), dim=1)
+#         mask = torch.sigmoid(mask)
+#
+#         offset_absmean = torch.mean(torch.abs(offset))
+#         if offset_absmean > 50:
+#             logger = get_root_logger()
+#             logger.warning(
+#                 f'Offset abs mean is {offset_absmean}, larger than 50.')
+#
+#         return modulated_deform_conv(x, offset, mask, self.weight, self.bias,
+#                                      self.stride, self.padding, self.dilation,
+#                                      self.groups, self.deformable_groups)
+
+
+class LayerNormFunction(torch.autograd.Function):
+
+    @staticmethod
+    def forward(ctx, x, weight, bias, eps):
+        ctx.eps = eps
+        N, C, H, W = x.size()
+        mu = x.mean(1, keepdim=True)
+        var = (x - mu).pow(2).mean(1, keepdim=True)
+        y = (x - mu) / (var + eps).sqrt()
+        ctx.save_for_backward(y, var, weight)
+        y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)
+        return y
+
+    @staticmethod
+    def backward(ctx, grad_output):
+        eps = ctx.eps
+
+        N, C, H, W = grad_output.size()
+        y, var, weight = ctx.saved_variables
+        g = grad_output * weight.view(1, C, 1, 1)
+        mean_g = g.mean(dim=1, keepdim=True)
+
+        mean_gy = (g * y).mean(dim=1, keepdim=True)
+        gx = 1. / torch.sqrt(var + eps) * (g - y * mean_gy - mean_g)
+        return gx, (grad_output * y).sum(dim=3).sum(dim=2).sum(dim=0), grad_output.sum(dim=3).sum(dim=2).sum(
+            dim=0), None
+
+class LayerNorm2d(nn.Module):
+
+    def __init__(self, channels, eps=1e-6):
+        super(LayerNorm2d, self).__init__()
+        self.register_parameter('weight', nn.Parameter(torch.ones(channels)))
+        self.register_parameter('bias', nn.Parameter(torch.zeros(channels)))
+        self.eps = eps
+
+    def forward(self, x):
+        return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)
+
+# handle multiple input
+class MySequential(nn.Sequential):
+    def forward(self, *inputs):
+        for module in self._modules.values():
+            if type(inputs) == tuple:
+                inputs = module(*inputs)
+            else:
+                inputs = module(inputs)
+        return inputs
+
+import time
+def measure_inference_speed(model, data, max_iter=200, log_interval=50):
+    model.eval()
+
+    # the first several iterations may be very slow so skip them
+    num_warmup = 5
+    pure_inf_time = 0
+    fps = 0
+
+    # benchmark with 2000 image and take the average
+    for i in range(max_iter):
+
+        torch.cuda.synchronize()
+        start_time = time.perf_counter()
+
+        with torch.no_grad():
+            model(*data)
+
+        torch.cuda.synchronize()
+        elapsed = time.perf_counter() - start_time
+
+        if i >= num_warmup:
+            pure_inf_time += elapsed
+            if (i + 1) % log_interval == 0:
+                fps = (i + 1 - num_warmup) / pure_inf_time
+                print(
+                    f'Done image [{i + 1:<3}/ {max_iter}], '
+                    f'fps: {fps:.1f} img / s, '
+                    f'times per image: {1000 / fps:.1f} ms / img',
+                    flush=True)
+
+        if (i + 1) == max_iter:
+            fps = (i + 1 - num_warmup) / pure_inf_time
+            print(
+                f'Overall fps: {fps:.1f} img / s, '
+                f'times per image: {1000 / fps:.1f} ms / img',
+                flush=True)
+            break
+    return fps

archs/nafnet_utils/local_arch.py

@@ -0,0 +1,92 @@
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class AvgPool2d(nn.Module):
+    def __init__(self, kernel_size=None, base_size=None, auto_pad=True, fast_imp=False, train_size=None):
+        super().__init__()
+        self.kernel_size = kernel_size
+        self.base_size = base_size
+        self.auto_pad = auto_pad
+
+        # only used for fast implementation
+        self.fast_imp = fast_imp
+        self.rs = [5, 4, 3, 2, 1]
+        self.max_r1 = self.rs[0]
+        self.max_r2 = self.rs[0]
+        self.train_size = train_size
+
+    def extra_repr(self) -> str:
+        return 'kernel_size={}, base_size={}, stride={}, fast_imp={}'.format(
+            self.kernel_size, self.base_size, self.kernel_size, self.fast_imp
+        )
+
+    def forward(self, x):
+        if self.kernel_size is None and self.base_size:
+            train_size = self.train_size
+            if isinstance(self.base_size, int):
+                self.base_size = (self.base_size, self.base_size)
+            self.kernel_size = list(self.base_size)
+            self.kernel_size[0] = x.shape[2] * self.base_size[0] // train_size[-2]
+            self.kernel_size[1] = x.shape[3] * self.base_size[1] // train_size[-1]
+
+            # only used for fast implementation
+            self.max_r1 = max(1, self.rs[0] * x.shape[2] // train_size[-2])
+            self.max_r2 = max(1, self.rs[0] * x.shape[3] // train_size[-1])
+
+        if self.kernel_size[0] >= x.size(-2) and self.kernel_size[1] >= x.size(-1):
+            return F.adaptive_avg_pool2d(x, 1)
+
+        if self.fast_imp:  # Non-equivalent implementation but faster
+            h, w = x.shape[2:]
+            if self.kernel_size[0] >= h and self.kernel_size[1] >= w:
+                out = F.adaptive_avg_pool2d(x, 1)
+            else:
+                r1 = [r for r in self.rs if h % r == 0][0]
+                r2 = [r for r in self.rs if w % r == 0][0]
+                # reduction_constraint
+                r1 = min(self.max_r1, r1)
+                r2 = min(self.max_r2, r2)
+                s = x[:, :, ::r1, ::r2].cumsum(dim=-1).cumsum(dim=-2)
+                n, c, h, w = s.shape
+                k1, k2 = min(h - 1, self.kernel_size[0] // r1), min(w - 1, self.kernel_size[1] // r2)
+                out = (s[:, :, :-k1, :-k2] - s[:, :, :-k1, k2:] - s[:, :, k1:, :-k2] + s[:, :, k1:, k2:]) / (k1 * k2)
+                out = torch.nn.functional.interpolate(out, scale_factor=(r1, r2))
+        else:
+            n, c, h, w = x.shape
+            s = x.cumsum(dim=-1).cumsum_(dim=-2)
+            s = torch.nn.functional.pad(s, (1, 0, 1, 0))  # pad 0 for convenience
+            k1, k2 = min(h, self.kernel_size[0]), min(w, self.kernel_size[1])
+            s1, s2, s3, s4 = s[:, :, :-k1, :-k2], s[:, :, :-k1, k2:], s[:, :, k1:, :-k2], s[:, :, k1:, k2:]
+            out = s4 + s1 - s2 - s3
+            out = out / (k1 * k2)
+
+        if self.auto_pad:
+            n, c, h, w = x.shape
+            _h, _w = out.shape[2:]
+            # print(x.shape, self.kernel_size)
+            pad2d = ((w - _w) // 2, (w - _w + 1) // 2, (h - _h) // 2, (h - _h + 1) // 2)
+            out = torch.nn.functional.pad(out, pad2d, mode='replicate')
+
+        return out
+
+def replace_layers(model, base_size, train_size, fast_imp, **kwargs):
+    for n, m in model.named_children():
+        if len(list(m.children())) > 0:
+            ## compound module, go inside it
+            replace_layers(m, base_size, train_size, fast_imp, **kwargs)
+
+        if isinstance(m, nn.AdaptiveAvgPool2d):
+            pool = AvgPool2d(base_size=base_size, fast_imp=fast_imp, train_size=train_size)
+            assert m.output_size == 1
+            setattr(model, n, pool)
+
+
+
+class Local_Base():
+    def convert(self, *args, train_size, **kwargs):
+        replace_layers(self, *args, train_size=train_size, **kwargs)
+        imgs = torch.rand(train_size)
+        with torch.no_grad():
+            self.forward(imgs)

archs/network.py

@@ -0,0 +1,143 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import functools
+try:
+    from .arch_util import EBlock, Attention_Light
+    from .arch_util_freq import EBlock_freq
+except:
+    from arch_util import EBlock, Attention_Light
+    from arch_util_freq import EBlock_freq
+
+
+class Network(nn.Module):
+    
+    def __init__(self, img_channel=3, 
+                 width=16, 
+                 middle_blk_num=1, 
+                 enc_blk_nums=[], 
+                 dec_blk_nums=[],  
+                 dilations = [1], 
+                 extra_depth_wise = False):
+        super(Network, self).__init__()
+        
+        self.intro = nn.Conv2d(in_channels=img_channel, out_channels=width, kernel_size=3, padding=1, stride=1, groups=1,
+                                bias=True)
+        self.ending = nn.Conv2d(in_channels=width, out_channels=img_channel, kernel_size=3, padding=1, stride=1, groups=1,
+                              bias=True)
+
+        self.encoders = nn.ModuleList()
+        self.decoders = nn.ModuleList()
+        self.middle_blks = nn.ModuleList()
+        self.ups = nn.ModuleList()
+        self.downs = nn.ModuleList()
+
+        chan = width
+        for num in enc_blk_nums:
+            self.encoders.append(
+                nn.Sequential(
+                    *[EBlock(chan, dilations = dilations, extra_depth_wise=extra_depth_wise) for _ in range(num)]
+                )
+            )
+            self.downs.append(
+                nn.Conv2d(chan, 2*chan, 2, 2)
+            )
+            chan = chan * 2
+
+        self.middle_blks = \
+            nn.Sequential(
+                *[EBlock(chan, dilations = dilations, extra_depth_wise=extra_depth_wise) for _ in range(middle_blk_num)]
+            )
+
+        for num in dec_blk_nums:
+            self.ups.append(
+                nn.Sequential(
+                    nn.Conv2d(chan, chan * 2, 1, bias=False),
+                    nn.PixelShuffle(2)
+                )
+            )
+            chan = chan // 2
+            self.decoders.append(
+                nn.Sequential(
+                    *[EBlock(chan, extra_depth_wise=extra_depth_wise) for _ in range(num)]
+                )
+            )
+
+        self.padder_size = 2 ** len(self.encoders)        
+        
+        #define the attention layers 
+        
+        # self.recon_trunk_light = nn.Sequential(*[FBlock(c = chan * self.padder_size,
+        #                                         DW_Expand=2, FFN_Expand=2, dilations = dilations, 
+        #                                         extra_depth_wise = False) for i in range(residual_layers)])
+
+        # ResidualBlock_noBN_f = functools.partial(ResidualBlock_noBN, nf = width * self.padder_size)
+        # self.recon_trunk_light = make_layer(ResidualBlock_noBN_f, residual_layers)
+        
+   
+        
+    def forward(self, input):
+
+        _, _, H, W = input.shape
+
+        x = self.intro(input)
+        
+        encs = []
+        # i = 0
+        for encoder, down in zip(self.encoders, self.downs):
+            x = encoder(x)
+            # print(i, x.shape)
+            encs.append(x)
+            x = down(x)
+            # i += 1
+
+        x = self.middle_blks(x)
+        # print('3', x.shape)
+        # apply the mask
+        # x = x * mask
+        
+        # x = self.recon_trunk_light(x)
+        
+        for decoder, up, enc_skip in zip(self.decoders, self.ups, encs[::-1]):
+            x = up(x)
+            x = x + enc_skip
+            x = decoder(x)
+
+        x = self.ending(x)
+        x = x + input
+        
+        return x[:, :, :H, :W]
+
+
+if __name__ == '__main__':
+    
+    img_channel = 3
+    width = 32
+
+    enc_blks = [1, 2, 3]
+    middle_blk_num = 3
+    dec_blks = [3, 1, 1]
+    residual_layers = 2
+    dilations = [1, 4]
+    
+    net = Network(img_channel=img_channel, 
+                  width=width, 
+                  middle_blk_num=middle_blk_num,
+                  enc_blk_nums=enc_blks, 
+                  dec_blk_nums=dec_blks,
+                  dilations = dilations)
+
+    # NAF = NAFNet(img_channel=img_channel, width=width, middle_blk_num=middle_blk_num,
+    #                   enc_blk_nums=enc_blks, dec_blk_nums=dec_blks)
+
+    inp_shape = (3, 256, 256)
+
+    from ptflops import get_model_complexity_info
+
+    macs, params = get_model_complexity_info(net, inp_shape, verbose=False, print_per_layer_stat=False)
+
+    print(macs, params)    
+    inp = torch.randn(1, 3, 256, 256)
+    out = net(inp)
+    
+