Spaces:
Running
on
Zero
Running
on
Zero
File size: 19,551 Bytes
2ada650 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 |
# Based on EVA, BEIT, timm and DeiT code bases
# https://github.com/baaivision/EVA
# https://github.com/rwightman/pytorch-image-models/tree/master/timm
# https://github.com/microsoft/unilm/tree/master/beit
# https://github.com/facebookresearch/deit/
# https://github.com/facebookresearch/dino
# --------------------------------------------------------'
import math
from functools import partial
import torch
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_
from timm.models.registry import register_model
from minigpt4.common.dist_utils import download_cached_file
def _cfg(url='', **kwargs):
return {
'url': url,
'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
'crop_pct': .9, 'interpolation': 'bicubic',
'mean': (0.5, 0.5, 0.5), 'std': (0.5, 0.5, 0.5),
**kwargs
}
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) -> str:
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.drop(x)
# commit this for the orignal BERT implement
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., window_size=None, attn_head_dim=None):
super().__init__()
self.num_heads = num_heads
head_dim = dim // num_heads
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=False)
if qkv_bias:
self.q_bias = nn.Parameter(torch.zeros(all_head_dim))
self.v_bias = nn.Parameter(torch.zeros(all_head_dim))
else:
self.q_bias = None
self.v_bias = None
if window_size:
self.window_size = window_size
self.num_relative_distance = (2 * window_size[0] - 1) * (2 * window_size[1] - 1) + 3
self.relative_position_bias_table = nn.Parameter(
torch.zeros(self.num_relative_distance, num_heads)) # 2*Wh-1 * 2*Ww-1, nH
# cls to token & token 2 cls & cls to cls
# get pair-wise relative position index for each token inside the window
coords_h = torch.arange(window_size[0])
coords_w = torch.arange(window_size[1])
coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
relative_coords[:, :, 0] += window_size[0] - 1 # shift to start from 0
relative_coords[:, :, 1] += window_size[1] - 1
relative_coords[:, :, 0] *= 2 * window_size[1] - 1
relative_position_index = \
torch.zeros(size=(window_size[0] * window_size[1] + 1, ) * 2, dtype=relative_coords.dtype)
relative_position_index[1:, 1:] = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
relative_position_index[0, 0:] = self.num_relative_distance - 3
relative_position_index[0:, 0] = self.num_relative_distance - 2
relative_position_index[0, 0] = self.num_relative_distance - 1
self.register_buffer("relative_position_index", relative_position_index)
else:
self.window_size = None
self.relative_position_bias_table = None
self.relative_position_index = None
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, rel_pos_bias=None):
B, N, C = x.shape
qkv_bias = None
if self.q_bias is not None:
qkv_bias = torch.cat((self.q_bias, torch.zeros_like(self.v_bias, requires_grad=False), self.v_bias))
# qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)
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))
if self.relative_position_bias_table is not None:
relative_position_bias = \
self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
self.window_size[0] * self.window_size[1] + 1,
self.window_size[0] * self.window_size[1] + 1, -1) # Wh*Ww,Wh*Ww,nH
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
attn = attn + relative_position_bias.unsqueeze(0)
if rel_pos_bias is not None:
attn = attn + rel_pos_bias
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., init_values=None, act_layer=nn.GELU, norm_layer=nn.LayerNorm,
window_size=None, 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, window_size=window_size, 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)
if init_values is not None and init_values > 0:
self.gamma_1 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
self.gamma_2 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
else:
self.gamma_1, self.gamma_2 = None, None
def forward(self, x, rel_pos_bias=None):
if self.gamma_1 is None:
x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias))
x = x + self.drop_path(self.mlp(self.norm2(x)))
else:
x = x + self.drop_path(self.gamma_1 * self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias))
x = x + self.drop_path(self.gamma_2 * 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):
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])
self.patch_shape = (img_size[0] // patch_size[0], 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)
def forward(self, x, **kwargs):
B, C, H, W = x.shape
# FIXME look at relaxing size constraints
assert H == self.img_size[0] and W == self.img_size[1], \
f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
x = self.proj(x).flatten(2).transpose(1, 2)
return x
class RelativePositionBias(nn.Module):
def __init__(self, window_size, num_heads):
super().__init__()
self.window_size = window_size
self.num_relative_distance = (2 * window_size[0] - 1) * (2 * window_size[1] - 1) + 3
self.relative_position_bias_table = nn.Parameter(
torch.zeros(self.num_relative_distance, num_heads)) # 2*Wh-1 * 2*Ww-1, nH
# cls to token & token 2 cls & cls to cls
# get pair-wise relative position index for each token inside the window
coords_h = torch.arange(window_size[0])
coords_w = torch.arange(window_size[1])
coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
relative_coords[:, :, 0] += window_size[0] - 1 # shift to start from 0
relative_coords[:, :, 1] += window_size[1] - 1
relative_coords[:, :, 0] *= 2 * window_size[1] - 1
relative_position_index = \
torch.zeros(size=(window_size[0] * window_size[1] + 1,) * 2, dtype=relative_coords.dtype)
relative_position_index[1:, 1:] = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
relative_position_index[0, 0:] = self.num_relative_distance - 3
relative_position_index[0:, 0] = self.num_relative_distance - 2
relative_position_index[0, 0] = self.num_relative_distance - 1
self.register_buffer("relative_position_index", relative_position_index)
# trunc_normal_(self.relative_position_bias_table, std=.02)
def forward(self):
relative_position_bias = \
self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
self.window_size[0] * self.window_size[1] + 1,
self.window_size[0] * self.window_size[1] + 1, -1) # Wh*Ww,Wh*Ww,nH
return relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
class VisionTransformer(nn.Module):
""" Vision Transformer with support for patch or hybrid CNN input stage
"""
def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, 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., norm_layer=nn.LayerNorm, init_values=None,
use_abs_pos_emb=True, use_rel_pos_bias=False, use_shared_rel_pos_bias=False,
use_mean_pooling=True, init_scale=0.001, use_checkpoint=False):
super().__init__()
self.image_size = img_size
self.num_classes = num_classes
self.num_features = self.embed_dim = embed_dim # num_features for consistency with other models
self.patch_embed = PatchEmbed(
img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
num_patches = self.patch_embed.num_patches
self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
if use_abs_pos_emb:
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
else:
self.pos_embed = None
self.pos_drop = nn.Dropout(p=drop_rate)
if use_shared_rel_pos_bias:
self.rel_pos_bias = RelativePositionBias(window_size=self.patch_embed.patch_shape, num_heads=num_heads)
else:
self.rel_pos_bias = None
self.use_checkpoint = use_checkpoint
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule
self.use_rel_pos_bias = use_rel_pos_bias
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,
init_values=init_values, window_size=self.patch_embed.patch_shape if use_rel_pos_bias else None)
for i in range(depth)])
# self.norm = nn.Identity() if use_mean_pooling else norm_layer(embed_dim)
# self.fc_norm = norm_layer(embed_dim) if use_mean_pooling else None
# self.head = nn.Linear(embed_dim, num_classes) if num_classes > 0 else nn.Identity()
if self.pos_embed is not None:
trunc_normal_(self.pos_embed, std=.02)
trunc_normal_(self.cls_token, std=.02)
# trunc_normal_(self.mask_token, std=.02)
# if isinstance(self.head, nn.Linear):
# trunc_normal_(self.head.weight, std=.02)
self.apply(self._init_weights)
self.fix_init_weight()
# if isinstance(self.head, nn.Linear):
# self.head.weight.data.mul_(init_scale)
# self.head.bias.data.mul_(init_scale)
def fix_init_weight(self):
def rescale(param, layer_id):
param.div_(math.sqrt(2.0 * layer_id))
for layer_id, layer in enumerate(self.blocks):
rescale(layer.attn.proj.weight.data, layer_id + 1)
rescale(layer.mlp.fc2.weight.data, layer_id + 1)
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 get_classifier(self):
return self.head
def reset_classifier(self, num_classes, global_pool=''):
self.num_classes = num_classes
self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
def forward_features(self, x):
x = self.patch_embed(x)
batch_size, seq_len, _ = x.size()
cls_tokens = self.cls_token.expand(batch_size, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
x = torch.cat((cls_tokens, x), dim=1)
if self.pos_embed is not None:
x = x + self.pos_embed
x = self.pos_drop(x)
rel_pos_bias = self.rel_pos_bias() if self.rel_pos_bias is not None else None
for blk in self.blocks:
if self.use_checkpoint:
x = checkpoint.checkpoint(blk, x, rel_pos_bias)
else:
x = blk(x, rel_pos_bias)
return x
# x = self.norm(x)
# if self.fc_norm is not None:
# t = x[:, 1:, :]
# return self.fc_norm(t.mean(1))
# else:
# return x[:, 0]
def forward(self, x):
x = self.forward_features(x)
# x = self.head(x)
return x
def get_intermediate_layers(self, x):
x = self.patch_embed(x)
batch_size, seq_len, _ = x.size()
cls_tokens = self.cls_token.expand(batch_size, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
x = torch.cat((cls_tokens, x), dim=1)
if self.pos_embed is not None:
x = x + self.pos_embed
x = self.pos_drop(x)
features = []
rel_pos_bias = self.rel_pos_bias() if self.rel_pos_bias is not None else None
for blk in self.blocks:
x = blk(x, rel_pos_bias)
features.append(x)
return features
def interpolate_pos_embed(model, checkpoint_model):
if 'pos_embed' in checkpoint_model:
pos_embed_checkpoint = checkpoint_model['pos_embed'].float()
embedding_size = pos_embed_checkpoint.shape[-1]
num_patches = model.patch_embed.num_patches
num_extra_tokens = model.pos_embed.shape[-2] - num_patches
# height (== width) for the checkpoint position embedding
orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5)
# height (== width) for the new position embedding
new_size = int(num_patches ** 0.5)
# class_token and dist_token are kept unchanged
if orig_size != new_size:
print("Position interpolate from %dx%d to %dx%d" % (orig_size, orig_size, new_size, new_size))
extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens]
# only the position tokens are interpolated
pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:]
pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
pos_tokens = torch.nn.functional.interpolate(
pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False)
pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2)
new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1)
checkpoint_model['pos_embed'] = new_pos_embed
def convert_weights_to_fp16(model: nn.Module):
"""Convert applicable model parameters to fp16"""
def _convert_weights_to_fp16(l):
if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Linear)):
l.weight.data = l.weight.data.half()
if l.bias is not None:
l.bias.data = l.bias.data.half()
# if isinstance(l, (nn.MultiheadAttention, Attention)):
# for attr in [*[f"{s}_proj_weight" for s in ["in", "q", "k", "v"]], "in_proj_bias", "bias_k", "bias_v"]:
# tensor = getattr(l, attr)
# if tensor is not None:
# tensor.data = tensor.data.half()
model.apply(_convert_weights_to_fp16)
def create_eva_vit_g(img_size=224,drop_path_rate=0.4,use_checkpoint=False,precision="fp16"):
model = VisionTransformer(
img_size=img_size,
patch_size=14,
use_mean_pooling=False,
embed_dim=1408,
depth=39,
# depth = 37,
num_heads=1408//88,
mlp_ratio=4.3637,
qkv_bias=True,
drop_path_rate=drop_path_rate,
norm_layer=partial(nn.LayerNorm, eps=1e-6),
use_checkpoint=use_checkpoint,
)
url = "https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/eva_vit_g.pth"
cached_file = download_cached_file(
url, check_hash=False, progress=True
)
state_dict = torch.load(cached_file, map_location="cpu")
interpolate_pos_embed(model,state_dict)
incompatible_keys = model.load_state_dict(state_dict, strict=False)
# print(incompatible_keys)
if precision == "fp16":
# model.to("cuda")
convert_weights_to_fp16(model)
return model |