File size: 10,645 Bytes
bc90483 | 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 | # Copyright (c) Meta Platforms, Inc. and affiliates.
#
# This software may be used and distributed in accordance with
# the terms of the DINOv3 License Agreement.
# ------------------------------------------------------------------------
# Plain-DETR
# Copyright (c) 2023 Xi'an Jiaotong University & Microsoft Research Asia.
# Licensed under The MIT License [see LICENSE for details]
# ------------------------------------------------------------------------
# -*- coding: utf-8 -*-
import torch
import torch.nn as nn
import torch.utils.checkpoint as checkpoint
from ..util.misc import _get_activation_fn, _get_clones, inverse_sigmoid
class GlobalCrossAttention(nn.Module):
def __init__(
self,
dim,
num_heads,
qkv_bias=True,
qk_scale=None,
attn_drop=0.0,
proj_drop=0.0,
):
super().__init__()
self.dim = dim
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim**-0.5
self.q = nn.Linear(dim, dim, bias=qkv_bias)
self.k = nn.Linear(dim, dim, bias=qkv_bias)
self.v = nn.Linear(dim, dim, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
self.softmax = nn.Softmax(dim=-1)
def forward(
self,
query,
k_input_flatten,
v_input_flatten,
input_padding_mask=None,
):
B_, N, C = k_input_flatten.shape
k = self.k(k_input_flatten).reshape(B_, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
v = self.v(v_input_flatten).reshape(B_, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
B_, N, C = query.shape
q = self.q(query).reshape(B_, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
attn_mask = None
if input_padding_mask is not None:
attn_mask = input_padding_mask[:, None, None] * -100
attn_mask = attn_mask.contiguous() # to enable efficient attention
x = torch.nn.functional.scaled_dot_product_attention(
query=q,
key=k,
value=v,
attn_mask=attn_mask,
dropout_p=self.attn_drop.p if self.training else 0,
scale=self.scale,
)
x = x.transpose(1, 2).reshape(B_, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class GlobalDecoderLayer(nn.Module):
def __init__(
self,
d_model=256,
d_ffn=1024,
dropout=0.1,
activation="relu",
n_heads=8,
norm_type="post_norm",
):
super().__init__()
self.norm_type = norm_type
# global cross attention
self.cross_attn = GlobalCrossAttention(d_model, n_heads)
self.dropout1 = nn.Dropout(dropout)
self.norm1 = nn.LayerNorm(d_model)
# self attention
self.self_attn = nn.MultiheadAttention(d_model, n_heads, dropout=dropout)
self.dropout2 = nn.Dropout(dropout)
self.norm2 = nn.LayerNorm(d_model)
# ffn
self.linear1 = nn.Linear(d_model, d_ffn)
self.activation = _get_activation_fn(activation)
self.dropout3 = nn.Dropout(dropout)
self.linear2 = nn.Linear(d_ffn, d_model)
self.dropout4 = nn.Dropout(dropout)
self.norm3 = nn.LayerNorm(d_model)
@staticmethod
def with_pos_embed(tensor, pos):
return tensor if pos is None else tensor + pos
def forward_pre(
self,
tgt,
query_pos,
src,
src_pos_embed,
src_padding_mask=None,
self_attn_mask=None,
):
# self attention
tgt2 = self.norm2(tgt)
q = k = self.with_pos_embed(tgt2, query_pos)
tgt2 = self.self_attn(
q.transpose(0, 1), k.transpose(0, 1), tgt2.transpose(0, 1), attn_mask=self_attn_mask, need_weights=False
)[0].transpose(0, 1)
tgt = tgt + self.dropout2(tgt2)
# global cross attention
tgt2 = self.norm1(tgt)
tgt2 = self.cross_attn(
self.with_pos_embed(tgt2, query_pos),
self.with_pos_embed(src, src_pos_embed),
src,
src_padding_mask,
)
tgt = tgt + self.dropout1(tgt2)
# ffn
tgt2 = self.norm3(tgt)
tgt2 = self.linear2(self.dropout3(self.activation(self.linear1(tgt2))))
tgt = tgt + self.dropout4(tgt2)
return tgt
def forward_post(
self,
tgt,
query_pos,
src,
src_pos_embed,
src_padding_mask=None,
self_attn_mask=None,
):
# self attention
q = k = self.with_pos_embed(tgt, query_pos)
tgt2 = self.self_attn(
q.transpose(0, 1), k.transpose(0, 1), tgt.transpose(0, 1), attn_mask=self_attn_mask, need_weights=False
)[0].transpose(0, 1)
tgt = tgt + self.dropout2(tgt2)
tgt = self.norm2(tgt)
# cross attention
tgt2 = self.cross_attn(
self.with_pos_embed(tgt, query_pos),
self.with_pos_embed(src, src_pos_embed),
src,
src_padding_mask,
)
tgt = tgt + self.dropout1(tgt2)
tgt = self.norm1(tgt)
# ffn
tgt2 = self.linear2(self.dropout3(self.activation(self.linear1(tgt))))
tgt = tgt + self.dropout4(tgt2)
tgt = self.norm3(tgt)
return tgt
def forward(
self,
tgt,
query_pos,
src,
src_pos_embed,
src_padding_mask=None,
self_attn_mask=None,
):
if self.norm_type == "pre_norm":
return self.forward_pre(tgt, query_pos, src, src_pos_embed, src_padding_mask, self_attn_mask)
if self.norm_type == "post_norm":
return self.forward_post(tgt, query_pos, src, src_pos_embed, src_padding_mask, self_attn_mask)
class GlobalDecoder(nn.Module):
def __init__(
self,
decoder_layer,
num_layers,
return_intermediate=False,
look_forward_twice=False,
use_checkpoint=False,
d_model=256,
norm_type="post_norm",
):
super().__init__()
self.layers = _get_clones(decoder_layer, num_layers)
self.num_layers = num_layers
self.return_intermediate = return_intermediate
self.look_forward_twice = look_forward_twice
self.use_checkpoint = use_checkpoint
# hack implementation for iterative bounding box refinement and two-stage Deformable DETR
self.bbox_embed = None
self.class_embed = None
self.norm_type = norm_type
if self.norm_type == "pre_norm":
self.final_layer_norm = nn.LayerNorm(d_model)
else:
self.final_layer_norm = None
def _reset_parameters(self):
# stolen from Swin Transformer
def _init_weights(m):
if isinstance(m, nn.Linear):
nn.init.trunc_normal_(m.weight, std=0.02)
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 forward(
self,
tgt,
reference_points,
src,
src_pos_embed,
src_spatial_shapes,
src_level_start_index,
src_valid_ratios,
query_pos=None,
src_padding_mask=None,
self_attn_mask=None,
max_shape=None,
):
output = tgt
intermediate = []
intermediate_reference_points = []
for lid, layer in enumerate(self.layers):
if self.use_checkpoint:
output = checkpoint.checkpoint(
layer,
output,
query_pos,
src,
src_pos_embed,
src_padding_mask,
self_attn_mask,
)
else:
output = layer(
output,
query_pos,
src,
src_pos_embed,
src_padding_mask,
self_attn_mask,
)
if self.final_layer_norm is not None:
output_after_norm = self.final_layer_norm(output)
else:
output_after_norm = output
# hack implementation for iterative bounding box refinement
if self.bbox_embed is not None:
tmp = self.bbox_embed[lid](output_after_norm)
if reference_points.shape[-1] == 4:
new_reference_points = tmp + inverse_sigmoid(reference_points)
new_reference_points = new_reference_points.sigmoid()
else:
assert reference_points.shape[-1] == 2
new_reference_points = tmp
new_reference_points[..., :2] = tmp[..., :2] + inverse_sigmoid(reference_points)
new_reference_points = new_reference_points.sigmoid()
reference_points = new_reference_points.detach()
if self.return_intermediate:
intermediate.append(output_after_norm)
intermediate_reference_points.append(
new_reference_points if self.look_forward_twice else reference_points
)
if self.return_intermediate:
return torch.stack(intermediate), torch.stack(intermediate_reference_points)
return output_after_norm, reference_points
def build_global_ape_decoder(args):
decoder_layer = GlobalDecoderLayer(
d_model=args.hidden_dim,
d_ffn=args.dim_feedforward,
dropout=args.dropout,
activation="relu",
n_heads=args.nheads,
norm_type=args.norm_type,
)
decoder = GlobalDecoder(
decoder_layer,
num_layers=args.dec_layers,
return_intermediate=True,
look_forward_twice=args.look_forward_twice,
use_checkpoint=args.decoder_use_checkpoint,
d_model=args.hidden_dim,
norm_type=args.norm_type,
)
return decoder
|