Spaces:
Configuration error
Configuration error
File size: 7,904 Bytes
3282b08 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 |
from torch import nn
import torch.nn.functional as F
import torch
from sync_batchnorm import SynchronizedBatchNorm2d as BatchNorm2d
def kp2gaussian(kp, spatial_size, kp_variance):
"""
Transform a keypoint into gaussian like representation
"""
mean = kp['value']
coordinate_grid = make_coordinate_grid(spatial_size, mean.type())
number_of_leading_dimensions = len(mean.shape) - 1
shape = (1,) * number_of_leading_dimensions + coordinate_grid.shape
coordinate_grid = coordinate_grid.view(*shape)
repeats = mean.shape[:number_of_leading_dimensions] + (1, 1, 1)
coordinate_grid = coordinate_grid.repeat(*repeats)
# Preprocess kp shape
shape = mean.shape[:number_of_leading_dimensions] + (1, 1, 2)
mean = mean.view(*shape)
mean_sub = (coordinate_grid - mean)
out = torch.exp(-0.5 * (mean_sub ** 2).sum(-1) / kp_variance)
return out
def make_coordinate_grid(spatial_size, type):
"""
Create a meshgrid [-1,1] x [-1,1] of given spatial_size.
"""
h, w = spatial_size
x = torch.arange(w).type(type)
y = torch.arange(h).type(type)
x = (2 * (x / (w - 1)) - 1)
y = (2 * (y / (h - 1)) - 1)
yy = y.view(-1, 1).repeat(1, w)
xx = x.view(1, -1).repeat(h, 1)
meshed = torch.cat([xx.unsqueeze_(2), yy.unsqueeze_(2)], 2)
return meshed
class ResBlock2d(nn.Module):
"""
Res block, preserve spatial resolution.
"""
def __init__(self, in_features, kernel_size, padding):
super(ResBlock2d, self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,
padding=padding)
self.conv2 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,
padding=padding)
self.norm1 = BatchNorm2d(in_features, affine=True)
self.norm2 = BatchNorm2d(in_features, affine=True)
def forward(self, x):
out = self.norm1(x)
out = F.relu(out)
out = self.conv1(out)
out = self.norm2(out)
out = F.relu(out)
out = self.conv2(out)
out += x
return out
class UpBlock2d(nn.Module):
"""
Upsampling block for use in decoder.
"""
def __init__(self, in_features, out_features, kernel_size=3, padding=1, groups=1):
super(UpBlock2d, self).__init__()
self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features, kernel_size=kernel_size,
padding=padding, groups=groups)
self.norm = BatchNorm2d(out_features, affine=True)
def forward(self, x):
out = F.interpolate(x, scale_factor=2)
out = self.conv(out)
out = self.norm(out)
out = F.relu(out)
return out
class DownBlock2d(nn.Module):
"""
Downsampling block for use in encoder.
"""
def __init__(self, in_features, out_features, kernel_size=3, padding=1, groups=1):
super(DownBlock2d, self).__init__()
self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features, kernel_size=kernel_size,
padding=padding, groups=groups)
self.norm = BatchNorm2d(out_features, affine=True)
self.pool = nn.AvgPool2d(kernel_size=(2, 2))
def forward(self, x):
out = self.conv(x)
out = self.norm(out)
out = F.relu(out)
out = self.pool(out)
return out
class SameBlock2d(nn.Module):
"""
Simple block, preserve spatial resolution.
"""
def __init__(self, in_features, out_features, groups=1, kernel_size=3, padding=1):
super(SameBlock2d, self).__init__()
self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features,
kernel_size=kernel_size, padding=padding, groups=groups)
self.norm = BatchNorm2d(out_features, affine=True)
def forward(self, x):
out = self.conv(x)
out = self.norm(out)
out = F.relu(out)
return out
class Encoder(nn.Module):
"""
Hourglass Encoder
"""
def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):
super(Encoder, self).__init__()
down_blocks = []
for i in range(num_blocks):
down_blocks.append(DownBlock2d(in_features if i == 0 else min(max_features, block_expansion * (2 ** i)),
min(max_features, block_expansion * (2 ** (i + 1))),
kernel_size=3, padding=1))
self.down_blocks = nn.ModuleList(down_blocks)
def forward(self, x):
outs = [x]
for down_block in self.down_blocks:
outs.append(down_block(outs[-1]))
return outs
class Decoder(nn.Module):
"""
Hourglass Decoder
"""
def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):
super(Decoder, self).__init__()
up_blocks = []
for i in range(num_blocks)[::-1]:
in_filters = (1 if i == num_blocks - 1 else 2) * min(max_features, block_expansion * (2 ** (i + 1)))
out_filters = min(max_features, block_expansion * (2 ** i))
up_blocks.append(UpBlock2d(in_filters, out_filters, kernel_size=3, padding=1))
self.up_blocks = nn.ModuleList(up_blocks)
self.out_filters = block_expansion + in_features
def forward(self, x):
out = x.pop()
for up_block in self.up_blocks:
out = up_block(out)
skip = x.pop()
out = torch.cat([out, skip], dim=1)
return out
class Hourglass(nn.Module):
"""
Hourglass architecture.
"""
def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):
super(Hourglass, self).__init__()
self.encoder = Encoder(block_expansion, in_features, num_blocks, max_features)
self.decoder = Decoder(block_expansion, in_features, num_blocks, max_features)
self.out_filters = self.decoder.out_filters
def forward(self, x):
return self.decoder(self.encoder(x))
class AntiAliasInterpolation2d(nn.Module):
"""
Band-limited downsampling, for better preservation of the input signal.
"""
def __init__(self, channels, scale):
super(AntiAliasInterpolation2d, self).__init__()
sigma = (1 / scale - 1) / 2
kernel_size = 2 * round(sigma * 4) + 1
self.ka = kernel_size // 2
self.kb = self.ka - 1 if kernel_size % 2 == 0 else self.ka
kernel_size = [kernel_size, kernel_size]
sigma = [sigma, sigma]
# The gaussian kernel is the product of the
# gaussian function of each dimension.
kernel = 1
meshgrids = torch.meshgrid(
[
torch.arange(size, dtype=torch.float32)
for size in kernel_size
]
)
for size, std, mgrid in zip(kernel_size, sigma, meshgrids):
mean = (size - 1) / 2
kernel *= torch.exp(-(mgrid - mean) ** 2 / (2 * std ** 2))
# Make sure sum of values in gaussian kernel equals 1.
kernel = kernel / torch.sum(kernel)
# Reshape to depthwise convolutional weight
kernel = kernel.view(1, 1, *kernel.size())
kernel = kernel.repeat(channels, *[1] * (kernel.dim() - 1))
self.register_buffer('weight', kernel)
self.groups = channels
self.scale = scale
inv_scale = 1 / scale
self.int_inv_scale = int(inv_scale)
def forward(self, input):
if self.scale == 1.0:
return input
out = F.pad(input, (self.ka, self.kb, self.ka, self.kb))
out = F.conv2d(out, weight=self.weight, groups=self.groups)
out = out[:, :, ::self.int_inv_scale, ::self.int_inv_scale]
return out
|