File size: 9,087 Bytes
0def483 |
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 |
"""
HAT (Hybrid Attention Transformer) main model implementation.
"""
import torch
import torch.nn as nn
import math
from .components import (
RHAG, PatchEmbed, PatchUnEmbed, Upsample,
trunc_normal_, window_partition, to_2tuple
)
class HAT(nn.Module):
def __init__(self, img_size=64, patch_size=1, in_chans=3, embed_dim=96, depths=(6, 6, 6, 6),
num_heads=(6, 6, 6, 6), window_size=7, compress_ratio=3, squeeze_factor=30,
conv_scale=0.01, overlap_ratio=0.5, mlp_ratio=4., qkv_bias=True, qk_scale=None,
drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm,
ape=False, patch_norm=True, use_checkpoint=False, upscale=2, img_range=1.,
upsampler='', resi_connection='1conv', **kwargs):
super(HAT, self).__init__()
self.window_size = window_size
self.shift_size = window_size // 2
self.overlap_ratio = overlap_ratio
num_in_ch = in_chans
num_out_ch = in_chans
num_feat = 64
self.img_range = img_range
if in_chans == 3:
rgb_mean = (0.4488, 0.4371, 0.4040)
self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
else:
self.mean = torch.zeros(1, 1, 1, 1)
self.upscale = upscale
self.upsampler = upsampler
# relative position index
relative_position_index_SA = self.calculate_rpi_sa()
relative_position_index_OCA = self.calculate_rpi_oca()
self.register_buffer('relative_position_index_SA', relative_position_index_SA)
self.register_buffer('relative_position_index_OCA', relative_position_index_OCA)
# shallow feature extraction
self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)
# deep feature extraction
self.num_layers = len(depths)
self.embed_dim = embed_dim
self.ape = ape
self.patch_norm = patch_norm
self.num_features = embed_dim
self.mlp_ratio = mlp_ratio
# split image into non-overlapping patches
self.patch_embed = PatchEmbed(
img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
norm_layer=norm_layer if self.patch_norm else None)
num_patches = self.patch_embed.num_patches
patches_resolution = self.patch_embed.patches_resolution
self.patches_resolution = patches_resolution
# merge non-overlapping patches into image
self.patch_unembed = PatchUnEmbed(
img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
norm_layer=norm_layer if self.patch_norm else None)
# absolute position embedding
if self.ape:
self.absolute_pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
trunc_normal_(self.absolute_pos_embed, std=.02)
self.pos_drop = nn.Dropout(p=drop_rate)
# stochastic depth
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
# build Residual Hybrid Attention Groups (RHAG)
self.layers = nn.ModuleList()
for i_layer in range(self.num_layers):
layer = RHAG(
dim=embed_dim,
input_resolution=(patches_resolution[0], patches_resolution[1]),
depth=depths[i_layer],
num_heads=num_heads[i_layer],
window_size=window_size,
compress_ratio=compress_ratio,
squeeze_factor=squeeze_factor,
conv_scale=conv_scale,
overlap_ratio=overlap_ratio,
mlp_ratio=self.mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop=drop_rate,
attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
norm_layer=norm_layer,
downsample=None,
use_checkpoint=use_checkpoint,
img_size=img_size,
patch_size=patch_size,
resi_connection=resi_connection)
self.layers.append(layer)
self.norm = norm_layer(self.num_features)
# build the last conv layer in deep feature extraction
if resi_connection == '1conv':
self.conv_after_body = nn.Conv2d(embed_dim, embed_dim, 3, 1, 1)
elif resi_connection == 'identity':
self.conv_after_body = nn.Identity()
# high quality image reconstruction
if self.upsampler == 'pixelshuffle':
self.conv_before_upsample = nn.Sequential(
nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True))
self.upsample = Upsample(upscale, num_feat)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
def calculate_rpi_sa(self):
coords_h = torch.arange(self.window_size)
coords_w = torch.arange(self.window_size)
coords = torch.stack(torch.meshgrid([coords_h, coords_w]))
coords_flatten = torch.flatten(coords, 1)
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]
relative_coords = relative_coords.permute(1, 2, 0).contiguous()
relative_coords[:, :, 0] += self.window_size - 1
relative_coords[:, :, 1] += self.window_size - 1
relative_coords[:, :, 0] *= 2 * self.window_size - 1
relative_position_index = relative_coords.sum(-1)
return relative_position_index
def calculate_rpi_oca(self):
window_size_ori = self.window_size
window_size_ext = self.window_size + int(self.overlap_ratio * self.window_size)
coords_h = torch.arange(window_size_ori)
coords_w = torch.arange(window_size_ori)
coords_ori = torch.stack(torch.meshgrid([coords_h, coords_w]))
coords_ori_flatten = torch.flatten(coords_ori, 1)
coords_h = torch.arange(window_size_ext)
coords_w = torch.arange(window_size_ext)
coords_ext = torch.stack(torch.meshgrid([coords_h, coords_w]))
coords_ext_flatten = torch.flatten(coords_ext, 1)
relative_coords = coords_ext_flatten[:, None, :] - coords_ori_flatten[:, :, None]
relative_coords = relative_coords.permute(1, 2, 0).contiguous()
relative_coords[:, :, 0] += window_size_ori - window_size_ext + 1
relative_coords[:, :, 1] += window_size_ori - window_size_ext + 1
relative_coords[:, :, 0] *= window_size_ori + window_size_ext - 1
relative_position_index = relative_coords.sum(-1)
return relative_position_index
def calculate_mask(self, x_size):
h, w = x_size
img_mask = torch.zeros((1, h, w, 1))
h_slices = (slice(0, -self.window_size), slice(-self.window_size, -self.shift_size), slice(-self.shift_size, None))
w_slices = (slice(0, -self.window_size), slice(-self.window_size, -self.shift_size), slice(-self.shift_size, None))
cnt = 0
for h in h_slices:
for w in w_slices:
img_mask[:, h, w, :] = cnt
cnt += 1
mask_windows = window_partition(img_mask, self.window_size)
mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
return attn_mask
@torch.jit.ignore
def no_weight_decay(self):
return {'absolute_pos_embed'}
@torch.jit.ignore
def no_weight_decay_keywords(self):
return {'relative_position_bias_table'}
def forward_features(self, x):
x_size = (x.shape[2], x.shape[3])
attn_mask = self.calculate_mask(x_size).to(x.device)
params = {'attn_mask': attn_mask, 'rpi_sa': self.relative_position_index_SA, 'rpi_oca': self.relative_position_index_OCA}
x = self.patch_embed(x)
if self.ape:
x = x + self.absolute_pos_embed
x = self.pos_drop(x)
for layer in self.layers:
x = layer(x, x_size, params)
x = self.norm(x)
x = self.patch_unembed(x, x_size)
return x
def forward(self, x):
self.mean = self.mean.type_as(x)
x = (x - self.mean) * self.img_range
if self.upsampler == 'pixelshuffle':
x = self.conv_first(x)
x = self.conv_after_body(self.forward_features(x)) + x
x = self.conv_before_upsample(x)
x = self.conv_last(self.upsample(x))
x = x / self.img_range + self.mean
return x |