Multiple modifications for experimental RRDB architectures
- Add LowDimRRDB; essentially a "normal RRDB" but the RDB blocks process at a low dimension using PixelShuffle - Add switching wrappers around it - Add support for switching on top of multi-headed inputs and outputs - Moves PixelUnshuffle to arch_util
This commit is contained in:
James Betker
parent
e89f28ead0
commit
532704af40
|
|
@ -3,19 +3,20 @@ import torch
|
|||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import models.archs.arch_util as arch_util
|
||||
from models.archs.arch_util import PixelUnshuffle
|
||||
import torchvision
|
||||
import switched_conv as switched_conv
|
||||
|
||||
|
||||
class ResidualDenseBlock_5C(nn.Module):
|
||||
def __init__(self, nf=64, gc=32, bias=True):
|
||||
def __init__(self, nf=64, gc=32, bias=True, late_stage_kernel_size=3, late_stage_padding=1):
|
||||
super(ResidualDenseBlock_5C, self).__init__()
|
||||
# gc: growth channel, i.e. intermediate channels
|
||||
self.conv1 = nn.Conv2d(nf, gc, 3, 1, 1, bias=bias)
|
||||
self.conv2 = nn.Conv2d(nf + gc, gc, 3, 1, 1, bias=bias)
|
||||
self.conv3 = nn.Conv2d(nf + 2 * gc, gc, 3, 1, 1, bias=bias)
|
||||
self.conv4 = nn.Conv2d(nf + 3 * gc, gc, 3, 1, 1, bias=bias)
|
||||
self.conv5 = nn.Conv2d(nf + 4 * gc, nf, 3, 1, 1, bias=bias)
|
||||
self.conv3 = nn.Conv2d(nf + 2 * gc, gc, late_stage_kernel_size, 1, late_stage_padding, bias=bias)
|
||||
self.conv4 = nn.Conv2d(nf + 3 * gc, gc, late_stage_kernel_size, 1, late_stage_padding, bias=bias)
|
||||
self.conv5 = nn.Conv2d(nf + 4 * gc, nf, late_stage_kernel_size, 1, late_stage_padding, bias=bias)
|
||||
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
|
||||
|
||||
# initialization
|
||||
|
|
@ -32,9 +33,15 @@ class ResidualDenseBlock_5C(nn.Module):
|
|||
|
||||
|
||||
# Multiple 5-channel residual block that uses learned switching to diversify its outputs.
|
||||
# If multi_head_input=False: takes standard (b,f,w,h) input tensor; else takes (b,heads,f,w,h) input tensor. Note that the default RDB block does not support this format, so use SwitchedRDB_5C_MultiHead for this case.
|
||||
# If collapse_heads=True, outputs (b,f,w,h) tensor.
|
||||
# If collapse_heads=False, outputs (b,heads,f,w,h) tensor.
|
||||
class SwitchedRDB_5C(switched_conv.MultiHeadSwitchedAbstractBlock):
|
||||
def __init__(self, nf=64, gc=32, num_convs=8, num_heads=2, init_temperature=1):
|
||||
rdb5c = functools.partial(ResidualDenseBlock_5C, nf, gc)
|
||||
def __init__(self, nf=64, gc=32, num_convs=8, num_heads=2, init_temperature=1, multi_head_input=False, collapse_heads=True, force_block=None):
|
||||
if force_block is None:
|
||||
rdb5c = functools.partial(ResidualDenseBlock_5C, nf, gc)
|
||||
else:
|
||||
rdb5c = force_block
|
||||
super(SwitchedRDB_5C, self).__init__(
|
||||
rdb5c,
|
||||
nf,
|
||||
|
|
@ -43,22 +50,70 @@ class SwitchedRDB_5C(switched_conv.MultiHeadSwitchedAbstractBlock):
|
|||
att_kernel_size=3,
|
||||
att_pads=1,
|
||||
initial_temperature=init_temperature,
|
||||
multi_head_input=multi_head_input,
|
||||
concat_heads_into_filters=collapse_heads,
|
||||
)
|
||||
self.mhead_collapse = nn.Conv2d(num_heads * nf, nf, 1)
|
||||
self.collapse_heads = collapse_heads
|
||||
if self.collapse_heads:
|
||||
self.mhead_collapse = nn.Conv2d(num_heads * nf, nf, 1)
|
||||
arch_util.initialize_weights([self.mhead_collapse], 1)
|
||||
|
||||
arch_util.initialize_weights([sw.attention_conv1 for sw in self.switches] +
|
||||
[sw.attention_conv2 for sw in self.switches] +
|
||||
[self.mhead_collapse], 1)
|
||||
[sw.attention_conv2 for sw in self.switches], 1)
|
||||
|
||||
def forward(self, x, output_attention_weights=False):
|
||||
outs = super(SwitchedRDB_5C, self).forward(x, output_attention_weights)
|
||||
if output_attention_weights:
|
||||
outs, atts = outs
|
||||
# outs need to be collapsed back down to a single heads worth of data.
|
||||
out = self.mhead_collapse(outs)
|
||||
|
||||
if self.collapse_heads:
|
||||
# outs need to be collapsed back down to a single heads worth of data.
|
||||
out = self.mhead_collapse(outs)
|
||||
else:
|
||||
out = outs
|
||||
|
||||
return out, atts
|
||||
|
||||
|
||||
# Implementation of ResidualDenseBlock_5C which compresses multiple switching heads via a Conv3d before doing RDB
|
||||
# computation.
|
||||
class ResidualDenseBlock_5C_WithMheadConverter(ResidualDenseBlock_5C):
|
||||
def __init__(self, nf=64, gc=32, bias=True, heads=2):
|
||||
# Switched blocks generally operate at low resolution, kernel size is much less important, therefore set to 1.
|
||||
super(ResidualDenseBlock_5C_WithMheadConverter, self).__init__(nf=nf, gc=gc, bias=bias, late_stage_kernel_size=1,
|
||||
late_stage_padding=0)
|
||||
self.heads = heads
|
||||
self.converter = nn.Conv3d(nf, nf, kernel_size=(heads, 1, 1), stride=(heads, 1, 1))
|
||||
|
||||
# Accepts input of shape (b, heads, f, w, h)
|
||||
def forward(self, x):
|
||||
# Permute filter dim to 1.
|
||||
x = x.permute(0, 2, 1, 3, 4)
|
||||
x = self.converter(x)
|
||||
x = torch.squeeze(x, dim=2)
|
||||
return super(ResidualDenseBlock_5C_WithMheadConverter, self).forward(x)
|
||||
|
||||
|
||||
# Multiple 5-channel residual block that uses learned switching to diversify its outputs. The difference between this
|
||||
# block and SwitchedRDB_5C is this block accepts multi-headed inputs of format (b,heads,f,w,h).
|
||||
#
|
||||
# It does this by performing a Conv3d on the first block, which convolves all heads and collapses them to a dimension
|
||||
# of 1. The tensor is then squeezed and performs identically to SwitchedRDB_5C from there.
|
||||
class SwitchedRDB_5C_MultiHead(SwitchedRDB_5C):
|
||||
def __init__(self, nf=64, gc=32, num_convs=8, num_heads=2, init_temperature=1, collapse_heads=False):
|
||||
rdb5c = functools.partial(ResidualDenseBlock_5C_WithMheadConverter, nf, gc, heads=num_heads)
|
||||
super(SwitchedRDB_5C_MultiHead, self).__init__(
|
||||
nf=nf,
|
||||
gc=gc,
|
||||
num_convs=num_convs,
|
||||
num_heads=num_heads,
|
||||
init_temperature=init_temperature,
|
||||
multi_head_input=True,
|
||||
collapse_heads=collapse_heads,
|
||||
force_block=rdb5c,
|
||||
)
|
||||
|
||||
|
||||
class RRDB(nn.Module):
|
||||
'''Residual in Residual Dense Block'''
|
||||
|
||||
|
|
@ -74,13 +129,26 @@ class RRDB(nn.Module):
|
|||
out = self.RDB3(out)
|
||||
return out * 0.2 + x
|
||||
|
||||
|
||||
class LowDimRRDB(RRDB):
|
||||
def __init__(self, nf, gc=32, dimensional_adjustment=4):
|
||||
super(LowDimRRDB, self).__init__(nf * (dimensional_adjustment ** 2), gc * (dimensional_adjustment ** 2))
|
||||
self.unshuffle = PixelUnshuffle(dimensional_adjustment)
|
||||
self.shuffle = nn.PixelShuffle(dimensional_adjustment)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.unshuffle(x)
|
||||
x = super(LowDimRRDB, self).forward(x)
|
||||
return self.shuffle(x)
|
||||
|
||||
|
||||
# RRDB block that uses switching on the individual RDB modules that compose it to increase learning diversity.
|
||||
class SwitchedRRDB(RRDB):
|
||||
def __init__(self, nf, gc=32, num_convs=8, init_temperature=1, final_temperature_step=1):
|
||||
super(RRDB, self).__init__()
|
||||
self.RDB1 = SwitchedRDB_5C(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
self.RDB2 = SwitchedRDB_5C(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
self.RDB3 = SwitchedRDB_5C(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
def __init__(self, nf, gc=32, num_convs=8, init_temperature=1, final_temperature_step=1, switching_block=SwitchedRDB_5C):
|
||||
super(SwitchedRRDB, self).__init__(nf, gc)
|
||||
self.RDB1 = switching_block(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
self.RDB2 = switching_block(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
self.RDB3 = switching_block(nf, gc, num_convs=num_convs, init_temperature=init_temperature)
|
||||
self.init_temperature = init_temperature
|
||||
self.final_temperature_step = final_temperature_step
|
||||
self.running_mean = 0
|
||||
|
|
@ -116,6 +184,53 @@ class SwitchedRRDB(RRDB):
|
|||
self.running_mean = 0
|
||||
return val
|
||||
|
||||
|
||||
# Identical to LowDimRRDB but wraps an RRDB rather than inheriting from it. TODO: remove LowDimRRDB when backwards
|
||||
# compatibility is no longer desired.
|
||||
class LowDimRRDBWrapper(nn.Module):
|
||||
# Do not specify nf or gc on the partial_rrdb passed in. That will be done by the wrapper.
|
||||
def __init__(self, nf, partial_rrdb, gc=32, dimensional_adjustment=4):
|
||||
super(LowDimRRDBWrapper, self).__init__()
|
||||
self.rrdb = partial_rrdb(nf=nf * (dimensional_adjustment ** 2), gc=gc * (dimensional_adjustment ** 2))
|
||||
self.unshuffle = PixelUnshuffle(dimensional_adjustment)
|
||||
self.shuffle = nn.PixelShuffle(dimensional_adjustment)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.unshuffle(x)
|
||||
x = self.rrdb(x)
|
||||
return self.shuffle(x)
|
||||
|
||||
# RRDB block that uses multi-headed switching on multiple individual RDB blocks to improve diversity. Multiple heads
|
||||
# are annealed internally. This variant has a depth of 4 RDB blocks, rather than 3 like others above.
|
||||
class SwitchedMultiHeadRRDB(SwitchedRRDB):
|
||||
def __init__(self, nf, gc=32, num_convs=8, num_heads=2, init_temperature=1, final_temperature_step=1):
|
||||
super(SwitchedMultiHeadRRDB, self).__init__(nf=nf, gc=gc, num_convs=num_convs, init_temperature=init_temperature, final_temperature_step=final_temperature_step)
|
||||
self.RDB1 = SwitchedRDB_5C(nf, gc, num_convs=num_convs, num_heads=num_heads, init_temperature=init_temperature, collapse_heads=False)
|
||||
self.RDB2 = SwitchedRDB_5C_MultiHead(nf, gc, num_convs=num_convs, num_heads=num_heads, init_temperature=init_temperature, collapse_heads=False)
|
||||
self.RDB3 = SwitchedRDB_5C_MultiHead(nf, gc, num_convs=num_convs, num_heads=num_heads, init_temperature=init_temperature, collapse_heads=False)
|
||||
self.RDB4 = SwitchedRDB_5C_MultiHead(nf, gc, num_convs=num_convs, num_heads=num_heads, init_temperature=init_temperature, collapse_heads=True)
|
||||
|
||||
def set_temperature(self, temp):
|
||||
[sw.set_attention_temperature(temp) for sw in self.RDB1.switches]
|
||||
[sw.set_attention_temperature(temp) for sw in self.RDB2.switches]
|
||||
[sw.set_attention_temperature(temp) for sw in self.RDB3.switches]
|
||||
[sw.set_attention_temperature(temp) for sw in self.RDB4.switches]
|
||||
|
||||
def forward(self, x):
|
||||
out, att1 = self.RDB1(x, True)
|
||||
out, att2 = self.RDB2(out, True)
|
||||
out, att3 = self.RDB3(out, True)
|
||||
out, att4 = self.RDB4(out, True)
|
||||
|
||||
a1mean, _ = switched_conv.compute_attention_specificity(att1, 2)
|
||||
a2mean, _ = switched_conv.compute_attention_specificity(att2, 2)
|
||||
a3mean, _ = switched_conv.compute_attention_specificity(att3, 2)
|
||||
a4mean, _ = switched_conv.compute_attention_specificity(att4, 2)
|
||||
self.running_mean += (a1mean + a2mean + a3mean + a4mean) / 3.0
|
||||
self.running_count += 1
|
||||
|
||||
return out * 0.2 + x
|
||||
|
||||
# This module performs the majority of the processing done by RRDBNet. It just doesn't have the upsampling at the end.
|
||||
class RRDBTrunk(nn.Module):
|
||||
def __init__(self, nf_in, nf_out, nb, gc=32, initial_stride=1, rrdb_block_f=None, conv_first_block=None):
|
||||
|
|
@ -295,21 +410,18 @@ class AssistedRRDBNet(nn.Module):
|
|||
|
||||
return (out,)
|
||||
|
||||
|
||||
class PixShuffleInitialConv(nn.Module):
|
||||
def __init__(self, reduction_factor, nf_out):
|
||||
super(PixShuffleInitialConv, self).__init__()
|
||||
self.conv = nn.Conv2d(3 * (reduction_factor ** 2), nf_out, 1)
|
||||
self.r = reduction_factor
|
||||
self.unshuffle = PixelUnshuffle(reduction_factor)
|
||||
|
||||
def forward(self, x):
|
||||
(b, f, w, h) = x.shape
|
||||
# This module can only be applied to input images (with 3 channels)
|
||||
assert f == 3
|
||||
# Perform a "reverse-pixel-shuffle", reducing the image size and increasing filter count by self.r**2
|
||||
x = x.contiguous().view(b, 3, w // self.r, self.r, h // self.r, self.r)
|
||||
x = x.permute(0, 1, 3, 5, 2, 4).contiguous().view(b, 3 * (self.r ** 2), w // self.r, h // self.r)
|
||||
# Apply the conv to bring the filter account to the desired size.
|
||||
|
||||
x = self.unshuffle(x)
|
||||
return self.conv(x)
|
||||
|
||||
# This class uses a RRDBTrunk to perform processing on an image, then upsamples it.
|
||||
|
|
@ -346,44 +458,4 @@ class PixShuffleRRDB(RRDBBase):
|
|||
fea = self.lrelu(self.upconv2(fea))
|
||||
out = self.conv_last(self.lrelu(self.HRconv(fea)))
|
||||
|
||||
return (out,)
|
||||
|
||||
|
||||
# This class uses two RRDB trunks to process an image at different resolution levels.
|
||||
class MultiRRDBNet(RRDBBase):
|
||||
def __init__(self, nf_base, gc_base, lo_blocks, hi_blocks, scale=2, rrdb_block_f=None):
|
||||
super(MultiRRDBNet, self).__init__()
|
||||
|
||||
# Chained trunks
|
||||
lo_nf = nf_base * 4
|
||||
lo_nf_out = nf_base // 4
|
||||
hi_nf = nf_base
|
||||
self.lo_trunk = RRDBTrunk(nf_base, lo_nf, lo_blocks, gc_base * 2, initial_stride=1, rrdb_block_f=rrdb_block_f, conv_first_block=PixShuffleInitialConv(4, lo_nf))
|
||||
self.skip_conv = nn.Conv2d(3, lo_nf_out, 1)
|
||||
self.hi_trunk = RRDBTrunk(lo_nf_out, hi_nf, hi_blocks, gc_base, initial_stride=1, rrdb_block_f=rrdb_block_f)
|
||||
self.trunks = [self.lo_trunk, self.hi_trunk]
|
||||
|
||||
# Upsampling
|
||||
self.scale = scale
|
||||
self.upconv1 = nn.Conv2d(hi_nf, hi_nf, 5, 1, padding=2, bias=True)
|
||||
self.upconv2 = nn.Conv2d(hi_nf, hi_nf, 5, 1, padding=2, bias=True)
|
||||
self.HRconv = nn.Conv2d(hi_nf, hi_nf, 5, 1, padding=2, bias=True)
|
||||
self.conv_last = nn.Conv2d(hi_nf, 3, 3, 1, 1, bias=True)
|
||||
self.pixel_shuffle = nn.PixelShuffle(4)
|
||||
|
||||
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
fea_lo = self.lo_trunk(x)
|
||||
fea = self.pixel_shuffle(fea_lo) + self.skip_conv(x)
|
||||
fea = self.hi_trunk(fea)
|
||||
|
||||
# Upsampling.
|
||||
fea = F.interpolate(fea, scale_factor=2, mode='nearest')
|
||||
fea = self.lrelu(self.upconv1(fea))
|
||||
if self.scale >= 4:
|
||||
fea = F.interpolate(fea, scale_factor=2, mode='nearest')
|
||||
fea = self.lrelu(self.upconv2(fea))
|
||||
out = self.conv_last(self.lrelu(self.HRconv(fea)))
|
||||
|
||||
return (out,)
|
||||
|
|
@ -128,3 +128,16 @@ def flow_warp(x, flow, interp_mode='bilinear', padding_mode='zeros'):
|
|||
vgrid_scaled = torch.stack((vgrid_x, vgrid_y), dim=3)
|
||||
output = F.grid_sample(x, vgrid_scaled, mode=interp_mode, padding_mode=padding_mode)
|
||||
return output
|
||||
|
||||
|
||||
class PixelUnshuffle(nn.Module):
|
||||
def __init__(self, reduction_factor):
|
||||
super(PixelUnshuffle, self).__init__()
|
||||
self.r = reduction_factor
|
||||
|
||||
def forward(self, x):
|
||||
(b, f, w, h) = x.shape
|
||||
x = x.contiguous().view(b, f, w // self.r, self.r, h // self.r, self.r)
|
||||
x = x.permute(0, 1, 3, 5, 2, 4).contiguous().view(b, f * (self.r ** 2), w // self.r, h // self.r)
|
||||
return x
|
||||
|
||||
|
|
|
|||
|
|
@ -38,14 +38,17 @@ def define_G(opt, net_key='network_G'):
|
|||
rrdb_block_f=functools.partial(RRDBNet_arch.SwitchedRRDB, nf=opt_net['nf'], gc=opt_net['gc'],
|
||||
init_temperature=opt_net['temperature'],
|
||||
final_temperature_step=opt_net['temperature_final_step']))
|
||||
elif which_model == 'MultiRRDBNet':
|
||||
block_f = None
|
||||
if opt_net['attention']:
|
||||
block_f = functools.partial(RRDBNet_arch.SwitchedRRDB, nf=opt_net['nf'], gc=opt_net['gc'],
|
||||
init_temperature=opt_net['temperature'],
|
||||
final_temperature_step=opt_net['temperature_final_step'])
|
||||
netG = RRDBNet_arch.MultiRRDBNet(nf_base=opt_net['nf'], gc_base=opt_net['gc'], lo_blocks=opt_net['lo_blocks'],
|
||||
hi_blocks=opt_net['hi_blocks'], scale=scale, rrdb_block_f=block_f)
|
||||
elif which_model == 'LowDimRRDBNet':
|
||||
rrdb = functools.partial(RRDBNet_arch.LowDimRRDB, nf=opt_net['nf'], gc=opt_net['gc'], dimensional_adjustment=opt_net['dim'])
|
||||
netG = RRDBNet_arch.RRDBNet(in_nc=opt_net['in_nc'], out_nc=opt_net['out_nc'],
|
||||
nf=opt_net['nf'], nb=opt_net['nb'], scale=scale, rrdb_block_f=rrdb)
|
||||
elif which_model == "LowDimRRDBWithMultiHeadSwitching":
|
||||
switcher = functools.partial(RRDBNet_arch.SwitchedMultiHeadRRDB, num_convs=opt_net['num_convs'], num_heads=opt_net['num_heads'],
|
||||
init_temperature=opt_net['temperature'], final_temperature_step=opt_net['temperature_final_step'])
|
||||
rrdb = functools.partial(RRDBNet_arch.LowDimRRDBWrapper, nf=opt_net['nf'], gc=opt_net['gc'], dimensional_adjustment=opt_net['dim'],
|
||||
partial_rrdb=switcher)
|
||||
netG = RRDBNet_arch.RRDBNet(in_nc=opt_net['in_nc'], out_nc=opt_net['out_nc'],
|
||||
nf=opt_net['nf'], nb=opt_net['nb'], scale=scale, rrdb_block_f=rrdb)
|
||||
elif which_model == 'PixRRDBNet':
|
||||
block_f = None
|
||||
if opt_net['attention']:
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user