Spaces:
Sleeping
Sleeping
File size: 7,568 Bytes
983684c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 |
import numpy as np
import torch
import torch.nn.functional as F
from torch import nn
from torch.nn import Linear, Conv2d, BatchNorm2d, PReLU, Sequential, Module
from model.encoder.encoders.helpers import get_blocks, Flatten, bottleneck_IR, bottleneck_IR_SE
from model.stylegan.model import EqualLinear
class GradualStyleBlock(Module):
def __init__(self, in_c, out_c, spatial):
super(GradualStyleBlock, self).__init__()
self.out_c = out_c
self.spatial = spatial
num_pools = int(np.log2(spatial))
modules = []
modules += [Conv2d(in_c, out_c, kernel_size=3, stride=2, padding=1),
nn.LeakyReLU()]
for i in range(num_pools - 1):
modules += [
Conv2d(out_c, out_c, kernel_size=3, stride=2, padding=1),
nn.LeakyReLU()
]
self.convs = nn.Sequential(*modules)
self.linear = EqualLinear(out_c, out_c, lr_mul=1)
def forward(self, x):
x = self.convs(x)
x = x.view(-1, self.out_c)
x = self.linear(x)
return x
class GradualStyleEncoder(Module):
def __init__(self, num_layers, mode='ir', opts=None):
super(GradualStyleEncoder, self).__init__()
assert num_layers in [50, 100, 152], 'num_layers should be 50,100, or 152'
assert mode in ['ir', 'ir_se'], 'mode should be ir or ir_se'
blocks = get_blocks(num_layers)
if mode == 'ir':
unit_module = bottleneck_IR
elif mode == 'ir_se':
unit_module = bottleneck_IR_SE
self.input_layer = Sequential(Conv2d(opts.input_nc, 64, (3, 3), 1, 1, bias=False),
BatchNorm2d(64),
PReLU(64))
modules = []
for block in blocks:
for bottleneck in block:
modules.append(unit_module(bottleneck.in_channel,
bottleneck.depth,
bottleneck.stride))
self.body = Sequential(*modules)
self.styles = nn.ModuleList()
self.style_count = opts.n_styles
self.coarse_ind = 3
self.middle_ind = 7
for i in range(self.style_count):
if i < self.coarse_ind:
style = GradualStyleBlock(512, 512, 16)
elif i < self.middle_ind:
style = GradualStyleBlock(512, 512, 32)
else:
style = GradualStyleBlock(512, 512, 64)
self.styles.append(style)
self.latlayer1 = nn.Conv2d(256, 512, kernel_size=1, stride=1, padding=0)
self.latlayer2 = nn.Conv2d(128, 512, kernel_size=1, stride=1, padding=0)
def _upsample_add(self, x, y):
'''Upsample and add two feature maps.
Args:
x: (Variable) top feature map to be upsampled.
y: (Variable) lateral feature map.
Returns:
(Variable) added feature map.
Note in PyTorch, when input size is odd, the upsampled feature map
with `F.upsample(..., scale_factor=2, mode='nearest')`
maybe not equal to the lateral feature map size.
e.g.
original input size: [N,_,15,15] ->
conv2d feature map size: [N,_,8,8] ->
upsampled feature map size: [N,_,16,16]
So we choose bilinear upsample which supports arbitrary output sizes.
'''
_, _, H, W = y.size()
return F.interpolate(x, size=(H, W), mode='bilinear', align_corners=True) + y
def forward(self, x):
x = self.input_layer(x)
latents = []
modulelist = list(self.body._modules.values())
for i, l in enumerate(modulelist):
x = l(x)
if i == 6:
c1 = x
elif i == 20:
c2 = x
elif i == 23:
c3 = x
for j in range(self.coarse_ind):
latents.append(self.styles[j](c3))
p2 = self._upsample_add(c3, self.latlayer1(c2))
for j in range(self.coarse_ind, self.middle_ind):
latents.append(self.styles[j](p2))
p1 = self._upsample_add(p2, self.latlayer2(c1))
for j in range(self.middle_ind, self.style_count):
latents.append(self.styles[j](p1))
out = torch.stack(latents, dim=1)
return out
class BackboneEncoderUsingLastLayerIntoW(Module):
def __init__(self, num_layers, mode='ir', opts=None):
super(BackboneEncoderUsingLastLayerIntoW, self).__init__()
print('Using BackboneEncoderUsingLastLayerIntoW')
assert num_layers in [50, 100, 152], 'num_layers should be 50,100, or 152'
assert mode in ['ir', 'ir_se'], 'mode should be ir or ir_se'
blocks = get_blocks(num_layers)
if mode == 'ir':
unit_module = bottleneck_IR
elif mode == 'ir_se':
unit_module = bottleneck_IR_SE
self.input_layer = Sequential(Conv2d(opts.input_nc, 64, (3, 3), 1, 1, bias=False),
BatchNorm2d(64),
PReLU(64))
self.output_pool = torch.nn.AdaptiveAvgPool2d((1, 1))
self.linear = EqualLinear(512, 512, lr_mul=1)
modules = []
for block in blocks:
for bottleneck in block:
modules.append(unit_module(bottleneck.in_channel,
bottleneck.depth,
bottleneck.stride))
self.body = Sequential(*modules)
def forward(self, x):
x = self.input_layer(x)
x = self.body(x)
x = self.output_pool(x)
x = x.view(-1, 512)
x = self.linear(x)
return x
class BackboneEncoderUsingLastLayerIntoWPlus(Module):
def __init__(self, num_layers, mode='ir', opts=None):
super(BackboneEncoderUsingLastLayerIntoWPlus, self).__init__()
print('Using BackboneEncoderUsingLastLayerIntoWPlus')
assert num_layers in [50, 100, 152], 'num_layers should be 50,100, or 152'
assert mode in ['ir', 'ir_se'], 'mode should be ir or ir_se'
blocks = get_blocks(num_layers)
if mode == 'ir':
unit_module = bottleneck_IR
elif mode == 'ir_se':
unit_module = bottleneck_IR_SE
self.n_styles = opts.n_styles
self.input_layer = Sequential(Conv2d(opts.input_nc, 64, (3, 3), 1, 1, bias=False),
BatchNorm2d(64),
PReLU(64))
self.output_layer_2 = Sequential(BatchNorm2d(512),
torch.nn.AdaptiveAvgPool2d((7, 7)),
Flatten(),
Linear(512 * 7 * 7, 512))
self.linear = EqualLinear(512, 512 * self.n_styles, lr_mul=1)
modules = []
for block in blocks:
for bottleneck in block:
modules.append(unit_module(bottleneck.in_channel,
bottleneck.depth,
bottleneck.stride))
self.body = Sequential(*modules)
def forward(self, x):
x = self.input_layer(x)
x = self.body(x)
x = self.output_layer_2(x)
x = self.linear(x)
x = x.view(-1, self.n_styles, 512)
return x
|