File size: 16,005 Bytes
663494c |
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 |
# ---------------------------------------------
# Copyright (c) OpenMMLab. All rights reserved.
# ---------------------------------------------
# Modified by Zhiqi Li
# ---------------------------------------------
from mmcv.ops.multi_scale_deform_attn import multi_scale_deformable_attn_pytorch
import mmcv
import cv2 as cv
import copy
import warnings
from matplotlib import pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import xavier_init, constant_init
from mmcv.cnn.bricks.registry import ATTENTION, TRANSFORMER_LAYER_SEQUENCE
from mmcv.cnn.bricks.transformer import TransformerLayerSequence
import math
from mmcv.runner.base_module import BaseModule, ModuleList, Sequential
from mmcv.utils import ConfigDict, build_from_cfg, deprecated_api_warning, to_2tuple
from mmcv.utils import ext_loader
from .multi_scale_deformable_attn_function import (
MultiScaleDeformableAttnFunction_fp32,
MultiScaleDeformableAttnFunction_fp16,
)
ext_module = ext_loader.load_ext(
"_ext", ["ms_deform_attn_backward", "ms_deform_attn_forward"]
)
from mmdet3d_plugin.uniad.custom_modules.peft import (LoRALinear, ZeroAdapter, LoRACLAdapter, LoRAMoECLAdapter,
finetuning_detach, frozen_grad, peft_wrapper_forward, lora_wrapper)
def inverse_sigmoid(x, eps=1e-5):
"""Inverse function of sigmoid.
Args:
x (Tensor): The tensor to do the
inverse.
eps (float): EPS avoid numerical
overflow. Defaults 1e-5.
Returns:
Tensor: The x has passed the inverse
function of sigmoid, has same
shape with input.
"""
x = x.clamp(min=0, max=1)
x1 = x.clamp(min=eps)
x2 = (1 - x).clamp(min=eps)
return torch.log(x1 / x2)
@TRANSFORMER_LAYER_SEQUENCE.register_module()
class DetectionTransformerDecoder(TransformerLayerSequence):
"""Implements the decoder in DETR3D transformer.
Args:
return_intermediate (bool): Whether to return intermediate outputs.
coder_norm_cfg (dict): Config of last normalization layer. Default：
`LN`.
"""
def __init__(self, *args, return_intermediate=False, **kwargs):
super(DetectionTransformerDecoder, self).__init__(*args, **kwargs)
self.return_intermediate = return_intermediate
self.fp16_enabled = False
def forward(
self,
query,
*args,
reference_points=None,
reg_branches=None,
key_padding_mask=None,
**kwargs,
):
"""Forward function for `Detr3DTransformerDecoder`.
Args:
query (Tensor): Input query with shape
`(num_query, bs, embed_dims)`.
reference_points (Tensor): The reference
points of offset. has shape
(bs, num_query, 4) when as_two_stage,
otherwise has shape ((bs, num_query, 2).
reg_branch: (obj:`nn.ModuleList`): Used for
refining the regression results. Only would
be passed when with_box_refine is True,
otherwise would be passed a `None`.
Returns:
Tensor: Results with shape [1, num_query, bs, embed_dims] when
return_intermediate is `False`, otherwise it has shape
[num_layers, num_query, bs, embed_dims].
"""
output = query
intermediate = []
intermediate_reference_points = []
for lid, layer in enumerate(self.layers):
reference_points_input = reference_points[..., :2].unsqueeze(
2
) # BS NUM_QUERY NUM_LEVEL 2
output = layer(
output,
*args,
reference_points=reference_points_input,
key_padding_mask=key_padding_mask,
**kwargs,
)
output = output.permute(1, 0, 2)
if reg_branches is not None:
tmp = reg_branches[lid](output)
assert reference_points.shape[-1] == 3
new_reference_points = torch.zeros_like(reference_points)
new_reference_points[..., :2] = tmp[..., :2] + inverse_sigmoid(
reference_points[..., :2]
)
new_reference_points[..., 2:3] = tmp[..., 4:5] + inverse_sigmoid(
reference_points[..., 2:3]
)
new_reference_points = new_reference_points.sigmoid()
reference_points = new_reference_points.detach()
output = output.permute(1, 0, 2)
if self.return_intermediate:
intermediate.append(output)
intermediate_reference_points.append(reference_points)
if self.return_intermediate:
return torch.stack(intermediate), torch.stack(intermediate_reference_points)
return output, reference_points
@ATTENTION.register_module()
class CustomMSDeformableAttention(BaseModule):
"""An attention module used in Deformable-Detr.
`Deformable DETR: Deformable Transformers for End-to-End Object Detection.
<https://arxiv.org/pdf/2010.04159.pdf>`_.
Args:
embed_dims (int): The embedding dimension of Attention.
Default: 256.
num_heads (int): Parallel attention heads. Default: 64.
num_levels (int): The number of feature map used in
Attention. Default: 4.
num_points (int): The number of sampling points for
each query in each head. Default: 4.
im2col_step (int): The step used in image_to_column.
Default: 64.
dropout (float): A Dropout layer on `inp_identity`.
Default: 0.1.
batch_first (bool): Key, Query and Value are shape of
(batch, n, embed_dim)
or (n, batch, embed_dim). Default to False.
norm_cfg (dict): Config dict for normalization layer.
Default: None.
init_cfg (obj:`mmcv.ConfigDict`): The Config for initialization.
Default: None.
"""
def __init__(
self,
embed_dims=256,
num_heads=8,
num_levels=4,
num_points=4,
im2col_step=64,
dropout=0.1,
batch_first=False,
norm_cfg=None,
init_cfg=None,
use_lora=False,
lora_rank=16,
lora_drop=0.
):
super().__init__(init_cfg)
if embed_dims % num_heads != 0:
raise ValueError(
f"embed_dims must be divisible by num_heads, "
f"but got {embed_dims} and {num_heads}"
)
dim_per_head = embed_dims // num_heads
self.norm_cfg = norm_cfg
self.dropout = nn.Dropout(dropout)
self.batch_first = batch_first
self.fp16_enabled = False
# you'd better set dim_per_head to a power of 2
# which is more efficient in the CUDA implementation
def _is_power_of_2(n):
if (not isinstance(n, int)) or (n < 0):
raise ValueError(
"invalid input for _is_power_of_2: {} (type: {})".format(n, type(n))
)
return (n & (n - 1) == 0) and n != 0
if not _is_power_of_2(dim_per_head):
warnings.warn(
"You'd better set embed_dims in "
"MultiScaleDeformAttention to make "
"the dimension of each attention head a power of 2 "
"which is more efficient in our CUDA implementation."
)
self.im2col_step = im2col_step
self.embed_dims = embed_dims
self.num_levels = num_levels
self.num_heads = num_heads
self.num_points = num_points
self.use_lora = use_lora
self.lora_rank = lora_rank
self.sampling_offsets = nn.Linear(
embed_dims, num_heads * num_levels * num_points * 2
)
self.attention_weights = nn.Linear(
embed_dims, num_heads * num_levels * num_points
)
self.value_proj = nn.Linear(embed_dims, embed_dims)
self.output_proj = nn.Linear(embed_dims, embed_dims)
if self.use_lora:
self.sampling_offsets_lora = LoRALinear(embed_dims, num_heads * num_levels * num_points * 2,
r=lora_rank, dropout=lora_drop)
self.attention_weights_lora = LoRALinear(embed_dims, num_heads * num_levels * num_points,
r=lora_rank, dropout=lora_drop)
self.value_proj_lora = LoRALinear(embed_dims, embed_dims, r=lora_rank, dropout=lora_drop)
self.output_proj_lora = LoRALinear(embed_dims, embed_dims, r=lora_rank, dropout=lora_drop)
self.init_weights()
def init_weights(self):
"""Default initialization for Parameters of Module."""
constant_init(self.sampling_offsets, 0.0)
thetas = torch.arange(self.num_heads, dtype=torch.float32) * (
2.0 * math.pi / self.num_heads
)
grid_init = torch.stack([thetas.cos(), thetas.sin()], -1)
grid_init = (
(grid_init / grid_init.abs().max(-1, keepdim=True)[0])
.view(self.num_heads, 1, 1, 2)
.repeat(1, self.num_levels, self.num_points, 1)
)
for i in range(self.num_points):
grid_init[:, :, i, :] *= i + 1
self.sampling_offsets.bias.data = grid_init.view(-1)
constant_init(self.attention_weights, val=0.0, bias=0.0)
xavier_init(self.value_proj, distribution="uniform", bias=0.0)
xavier_init(self.output_proj, distribution="uniform", bias=0.0)
if self.use_lora:
finetuning_detach(self)
self._is_init = True
@deprecated_api_warning(
{"residual": "identity"}, cls_name="MultiScaleDeformableAttention"
)
def forward(
self,
query,
key=None,
value=None,
identity=None,
query_pos=None,
key_padding_mask=None,
reference_points=None,
spatial_shapes=None,
level_start_index=None,
flag="decoder",
**kwargs,
):
"""Forward Function of MultiScaleDeformAttention.
Args:
query (Tensor): Query of Transformer with shape
(num_query, bs, embed_dims).
key (Tensor): The key tensor with shape
`(num_key, bs, embed_dims)`.
value (Tensor): The value tensor with shape
`(num_key, bs, embed_dims)`.
identity (Tensor): The tensor used for addition, with the
same shape as `query`. Default None. If None,
`query` will be used.
query_pos (Tensor): The positional encoding for `query`.
Default: None.
key_pos (Tensor): The positional encoding for `key`. Default
None.
reference_points (Tensor): The normalized reference
points with shape (bs, num_query, num_levels, 2),
all elements is range in [0, 1], top-left (0,0),
bottom-right (1, 1), including padding area.
or (N, Length_{query}, num_levels, 4), add
additional two dimensions is (w, h) to
form reference boxes.
key_padding_mask (Tensor): ByteTensor for `query`, with
shape [bs, num_key].
spatial_shapes (Tensor): Spatial shape of features in
different levels. With shape (num_levels, 2),
last dimension represents (h, w).
level_start_index (Tensor): The start index of each level.
A tensor has shape ``(num_levels, )`` and can be represented
as [0, h_0*w_0, h_0*w_0+h_1*w_1, ...].
Returns:
Tensor: forwarded results with shape [num_query, bs, embed_dims].
"""
if value is None:
value = query
if identity is None:
identity = query
if query_pos is not None:
query = query + query_pos
if not self.batch_first:
# change to (bs, num_query ,embed_dims)
query = query.permute(1, 0, 2)
value = value.permute(1, 0, 2)
bs, num_query, _ = query.shape
bs, num_value, _ = value.shape
assert (spatial_shapes[:, 0] * spatial_shapes[:, 1]).sum() == num_value
if self.use_lora:
value = self.value_proj(value) + self.value_proj_lora(value)
else:
value = self.value_proj(value)
if key_padding_mask is not None:
value = value.masked_fill(key_padding_mask[..., None], 0.0)
value = value.view(bs, num_value, self.num_heads, -1)
sampling_offsets = self.sampling_offsets(query).view(
bs, num_query, self.num_heads, self.num_levels, self.num_points, 2
)
attention_weights = self.attention_weights(query).view(
bs, num_query, self.num_heads, self.num_levels * self.num_points
)
if self.use_lora:
sampling_offsets += self.sampling_offsets_lora(query).view(
bs, num_query, self.num_heads, self.num_levels, self.num_points, 2
)
attention_weights += self.attention_weights_lora(query).view(
bs, num_query, self.num_heads, self.num_levels * self.num_points
)
attention_weights = attention_weights.softmax(-1)
attention_weights = attention_weights.view(
bs, num_query, self.num_heads, self.num_levels, self.num_points
)
if reference_points.shape[-1] == 2:
offset_normalizer = torch.stack(
[spatial_shapes[..., 1], spatial_shapes[..., 0]], -1
)
sampling_locations = (
reference_points[:, :, None, :, None, :]
+ sampling_offsets / offset_normalizer[None, None, None, :, None, :]
)
elif reference_points.shape[-1] == 4:
sampling_locations = (
reference_points[:, :, None, :, None, :2]
+ sampling_offsets
/ self.num_points
* reference_points[:, :, None, :, None, 2:]
* 0.5
)
else:
raise ValueError(
f"Last dim of reference_points must be"
f" 2 or 4, but get {reference_points.shape[-1]} instead."
)
if torch.cuda.is_available() and value.is_cuda:
# using fp16 deformable attention is unstable because it performs many sum operations
if value.dtype == torch.float16:
MultiScaleDeformableAttnFunction = MultiScaleDeformableAttnFunction_fp32
else:
MultiScaleDeformableAttnFunction = MultiScaleDeformableAttnFunction_fp32
output = MultiScaleDeformableAttnFunction.apply(
value,
spatial_shapes,
level_start_index,
sampling_locations,
attention_weights,
self.im2col_step,
)
else:
output = multi_scale_deformable_attn_pytorch(
value, spatial_shapes, sampling_locations, attention_weights
)
if self.use_lora:
output = self.output_proj(output) + self.output_proj_lora(output)
else:
output = self.output_proj(output)
if not self.batch_first:
# (num_query, bs ,embed_dims)
output = output.permute(1, 0, 2)
return self.dropout(output) + identity
|