Spaces:
Runtime error
Runtime error
File size: 12,660 Bytes
3424266 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 |
# --------------------------------------------------------
# Based on the ViTPose and 4DHumans code bases
# https://github.com/ViTAE-Transformer/ViTPose/
# https://github.com/shubham-goel/4D-Humans
# --------------------------------------------------------
import math
import torch
from functools import partial
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from timm.models.layers import drop_path, to_2tuple, trunc_normal_
def vit(cfg):
return ViT(
img_size=(256, 192),
patch_size=16,
embed_dim=1280,
depth=32,
num_heads=16,
ratio=1,
use_checkpoint=False,
mlp_ratio=4,
qkv_bias=True,
drop_path_rate=0.55,
)
def get_abs_pos(abs_pos, h, w, ori_h, ori_w, has_cls_token=True):
"""
Calculate absolute positional embeddings. If needed, resize embeddings and remove cls_token
dimension for the original embeddings.
Args:
abs_pos (Tensor): absolute positional embeddings with (1, num_position, C).
has_cls_token (bool): If true, has 1 embedding in abs_pos for cls token.
hw (Tuple): size of input image tokens.
Returns:
Absolute positional embeddings after processing with shape (1, H, W, C)
"""
cls_token = None
B, L, C = abs_pos.shape
if has_cls_token:
cls_token = abs_pos[:, 0:1]
abs_pos = abs_pos[:, 1:]
if ori_h != h or ori_w != w:
new_abs_pos = F.interpolate(
abs_pos.reshape(1, ori_h, ori_w, -1).permute(0, 3, 1, 2),
size=(h, w),
mode="bicubic",
align_corners=False,
).permute(0, 2, 3, 1).reshape(B, -1, C)
else:
new_abs_pos = abs_pos
if cls_token is not None:
new_abs_pos = torch.cat([cls_token, new_abs_pos], dim=1)
return new_abs_pos
class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"""
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
def forward(self, x):
return drop_path(x, self.drop_prob, self.training)
def extra_repr(self):
return 'p={}'.format(self.drop_prob)
class Mlp(nn.Module):
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Linear(in_features, hidden_features)
self.act = act_layer()
self.fc2 = nn.Linear(hidden_features, out_features)
self.drop = nn.Dropout(drop)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.fc2(x)
x = self.drop(x)
return x
class Attention(nn.Module):
def __init__(
self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.,
proj_drop=0., attn_head_dim=None,):
super().__init__()
self.num_heads = num_heads
head_dim = dim // num_heads
self.dim = dim
if attn_head_dim is not None:
head_dim = attn_head_dim
all_head_dim = head_dim * self.num_heads
self.scale = qk_scale or head_dim ** -0.5
self.qkv = nn.Linear(dim, all_head_dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(all_head_dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
def forward(self, x):
B, N, C = x.shape
qkv = self.qkv(x)
qkv = qkv.reshape(B, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
q = q * self.scale
attn = (q @ k.transpose(-2, -1))
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, N, -1)
x = self.proj(x)
x = self.proj_drop(x)
return x
class Block(nn.Module):
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None,
drop=0., attn_drop=0., drop_path=0., act_layer=nn.GELU,
norm_layer=nn.LayerNorm, attn_head_dim=None
):
super().__init__()
self.norm1 = norm_layer(dim)
self.attn = Attention(
dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
attn_drop=attn_drop, proj_drop=drop, attn_head_dim=attn_head_dim
)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = norm_layer(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
def forward(self, x):
x = x + self.drop_path(self.attn(self.norm1(x)))
x = x + self.drop_path(self.mlp(self.norm2(x)))
return x
class PatchEmbed(nn.Module):
""" Image to Patch Embedding
"""
def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, ratio=1):
super().__init__()
img_size = to_2tuple(img_size)
patch_size = to_2tuple(patch_size)
num_patches = (img_size[1] // patch_size[1]) * (img_size[0] // patch_size[0]) * (ratio ** 2)
self.patch_shape = (int(img_size[0] // patch_size[0] * ratio), int(img_size[1] // patch_size[1] * ratio))
self.origin_patch_shape = (int(img_size[0] // patch_size[0]), int(img_size[1] // patch_size[1]))
self.img_size = img_size
self.patch_size = patch_size
self.num_patches = num_patches
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=(patch_size[0] // ratio), padding=4 + 2 * (ratio//2-1))
def forward(self, x, **kwargs):
B, C, H, W = x.shape
x = self.proj(x)
Hp, Wp = x.shape[2], x.shape[3]
x = x.flatten(2).transpose(1, 2)
return x, (Hp, Wp)
class HybridEmbed(nn.Module):
""" CNN Feature Map Embedding
Extract feature map from CNN, flatten, project to embedding dim.
"""
def __init__(self, backbone, img_size=224, feature_size=None, in_chans=3, embed_dim=768):
super().__init__()
assert isinstance(backbone, nn.Module)
img_size = to_2tuple(img_size)
self.img_size = img_size
self.backbone = backbone
if feature_size is None:
with torch.no_grad():
training = backbone.training
if training:
backbone.eval()
o = self.backbone(torch.zeros(1, in_chans, img_size[0], img_size[1]))[-1]
feature_size = o.shape[-2:]
feature_dim = o.shape[1]
backbone.train(training)
else:
feature_size = to_2tuple(feature_size)
feature_dim = self.backbone.feature_info.channels()[-1]
self.num_patches = feature_size[0] * feature_size[1]
self.proj = nn.Linear(feature_dim, embed_dim)
def forward(self, x):
x = self.backbone(x)[-1]
x = x.flatten(2).transpose(1, 2)
x = self.proj(x)
return x
class ViT(nn.Module):
def __init__(self,
img_size=224, patch_size=16, in_chans=3, num_classes=80, embed_dim=768, depth=12,
num_heads=12, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0.,
drop_path_rate=0., hybrid_backbone=None, norm_layer=None, use_checkpoint=False,
frozen_stages=-1, ratio=1, last_norm=True,
patch_padding='pad', freeze_attn=False, freeze_ffn=False,
):
# Protect mutable default arguments
super(ViT, self).__init__()
norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
self.num_classes = num_classes
self.num_features = self.embed_dim = embed_dim # num_features for consistency with other models
self.frozen_stages = frozen_stages
self.use_checkpoint = use_checkpoint
self.patch_padding = patch_padding
self.freeze_attn = freeze_attn
self.freeze_ffn = freeze_ffn
self.depth = depth
if hybrid_backbone is not None:
self.patch_embed = HybridEmbed(
hybrid_backbone, img_size=img_size, in_chans=in_chans, embed_dim=embed_dim)
else:
self.patch_embed = PatchEmbed(
img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim, ratio=ratio)
num_patches = self.patch_embed.num_patches
# since the pretraining model has class token
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule
self.blocks = nn.ModuleList([
Block(
dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
)
for i in range(depth)])
self.last_norm = norm_layer(embed_dim) if last_norm else nn.Identity()
if self.pos_embed is not None:
trunc_normal_(self.pos_embed, std=.02)
self._freeze_stages()
def _freeze_stages(self):
"""Freeze parameters."""
if self.frozen_stages >= 0:
self.patch_embed.eval()
for param in self.patch_embed.parameters():
param.requires_grad = False
for i in range(1, self.frozen_stages + 1):
m = self.blocks[i]
m.eval()
for param in m.parameters():
param.requires_grad = False
if self.freeze_attn:
for i in range(0, self.depth):
m = self.blocks[i]
m.attn.eval()
m.norm1.eval()
for param in m.attn.parameters():
param.requires_grad = False
for param in m.norm1.parameters():
param.requires_grad = False
if self.freeze_ffn:
self.pos_embed.requires_grad = False
self.patch_embed.eval()
for param in self.patch_embed.parameters():
param.requires_grad = False
for i in range(0, self.depth):
m = self.blocks[i]
m.mlp.eval()
m.norm2.eval()
for param in m.mlp.parameters():
param.requires_grad = False
for param in m.norm2.parameters():
param.requires_grad = False
def init_weights(self):
"""Initialize the weights in backbone.
Args:
pretrained (str, optional): Path to pre-trained weights.
Defaults to None.
"""
def _init_weights(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)
self.apply(_init_weights)
def get_num_layers(self):
return len(self.blocks)
@torch.jit.ignore
def no_weight_decay(self):
return {'pos_embed', 'cls_token'}
def forward_features(self, x):
B, C, H, W = x.shape
x, (Hp, Wp) = self.patch_embed(x)
if self.pos_embed is not None:
# fit for multiple GPU training
# since the first element for pos embed (sin-cos manner) is zero, it will cause no difference
x = x + self.pos_embed[:, 1:] + self.pos_embed[:, :1]
for blk in self.blocks:
if self.use_checkpoint:
x = checkpoint.checkpoint(blk, x)
else:
x = blk(x)
x = self.last_norm(x)
xp = x.permute(0, 2, 1).reshape(B, -1, Hp, Wp).contiguous()
return xp
def forward(self, x):
x = self.forward_features(x)
return x
def train(self, mode=True):
"""Convert the model into training mode."""
super().train(mode)
self._freeze_stages()
|