231 lines
6.8 KiB
Python
231 lines
6.8 KiB
Python
# ------------------------------------------------------------------------
|
|
# Copyright (c) 2022 megvii-model. All Rights Reserved.
|
|
# ------------------------------------------------------------------------
|
|
|
|
'''
|
|
Simple Baselines for Image Restoration
|
|
|
|
'''
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
from basicsr.models.archs.arch_util import LayerNorm2d
|
|
from basicsr.models.archs.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)
|
|
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
|
|
|
|
x = self.norm1(x)
|
|
|
|
x = self.conv1(x)
|
|
x = self.conv2(x)
|
|
x = self.sg(x)
|
|
x = x * self.sca(x)
|
|
x = self.conv3(x)
|
|
|
|
x = self.dropout1(x)
|
|
|
|
y = inp + x * self.beta
|
|
|
|
x = self.conv4(self.norm2(y))
|
|
x = self.sg(x)
|
|
x = self.conv5(x)
|
|
|
|
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))
|
|
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)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
import resource
|
|
def using(point=""):
|
|
# print(f'using .. {point}')
|
|
usage = resource.getrusage(resource.RUSAGE_SELF)
|
|
global Total, LastMem
|
|
|
|
# if usage[2]/1024.0 - LastMem > 0.01:
|
|
# print(point, usage[2]/1024.0)
|
|
print(point, usage[2] / 1024.0)
|
|
|
|
LastMem = usage[2] / 1024.0
|
|
return usage[2] / 1024.0
|
|
|
|
img_channel = 3
|
|
width = 32
|
|
|
|
enc_blks = [2, 2, 2, 20]
|
|
middle_blk_num = 2
|
|
dec_blks = [2, 2, 2, 2]
|
|
|
|
print('enc blks', enc_blks, 'middle blk num', middle_blk_num, 'dec blks', dec_blks, 'width' , width)
|
|
|
|
using('start . ')
|
|
net = NAFNet(img_channel=img_channel, width=width, middle_blk_num=middle_blk_num,
|
|
enc_blk_nums=enc_blks, dec_blk_nums=dec_blks)
|
|
|
|
using('network .. ')
|
|
|
|
# for n, p in net.named_parameters()
|
|
# print(n, p.shape)
|
|
|
|
|
|
inp = torch.randn((4, 3, 256, 256))
|
|
|
|
out = net(inp)
|
|
final_mem = using('end .. ')
|
|
# out.sum().backward()
|
|
|
|
# out.sum().backward()
|
|
|
|
# using('backward .. ')
|
|
|
|
# exit(0)
|
|
|
|
inp_shape = (3, 512, 512)
|
|
|
|
from ptflops import get_model_complexity_info
|
|
|
|
macs, params = get_model_complexity_info(net, inp_shape, verbose=False, print_per_layer_stat=False)
|
|
|
|
params = float(params[:-3])
|
|
macs = float(macs[:-4])
|
|
|
|
print(macs, params)
|
|
|
|
print('total .. ', params * 8 + final_mem)
|
|
|
|
|
|
|