File size: 6,482 Bytes
2cd560a |
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 |
# ------------------------------------------------------------------------
# Copyright (c) 2022 megvii-research. All Rights Reserved.
# ------------------------------------------------------------------------
# Modified from Deformable DETR (https://github.com/fundamentalvision/Deformable-DETR)
# Copyright (c) 2020 SenseTime. All Rights Reserved.
# ------------------------------------------------------------------------
# Modified from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# ------------------------------------------------------------------------
from __future__ import absolute_import
from __future__ import print_function
from __future__ import division
import warnings
import math
import torch
from torch import nn
import torch.nn.functional as F
from torch.nn.init import xavier_uniform_, constant_
from ..functions import MSDeformAttnFunction
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
class MSDeformAttn(nn.Module):
def __init__(self, d_model=256, n_levels=4, n_heads=8, n_points=4, sigmoid_attn=False):
"""
Multi-Scale Deformable Attention Module
:param d_model hidden dimension
:param n_levels number of feature levels
:param n_heads number of attention heads
:param n_points number of sampling points per attention head per feature level
"""
super().__init__()
if d_model % n_heads != 0:
raise ValueError('d_model must be divisible by n_heads, but got {} and {}'.format(d_model, n_heads))
_d_per_head = d_model // n_heads
# you'd better set _d_per_head to a power of 2 which is more efficient in our CUDA implementation
if not _is_power_of_2(_d_per_head):
warnings.warn("You'd better set d_model in MSDeformAttn to make the dimension of each attention head a power of 2 "
"which is more efficient in our CUDA implementation.")
self.im2col_step = 64
self.sigmoid_attn = sigmoid_attn
self.d_model = d_model
self.n_levels = n_levels
self.n_heads = n_heads
self.n_points = n_points
self.sampling_offsets = nn.Linear(d_model, n_heads * n_levels * n_points * 2)
self.attention_weights = nn.Linear(d_model, n_heads * n_levels * n_points)
self.value_proj = nn.Linear(d_model, d_model)
self.output_proj = nn.Linear(d_model, d_model)
self._reset_parameters()
def _reset_parameters(self):
constant_(self.sampling_offsets.weight.data, 0.)
thetas = torch.arange(self.n_heads, dtype=torch.float32) * (2.0 * math.pi / self.n_heads)
grid_init = torch.stack([thetas.cos(), thetas.sin()], -1)
grid_init = (grid_init / grid_init.abs().max(-1, keepdim=True)[0]).view(self.n_heads, 1, 1, 2).repeat(1, self.n_levels, self.n_points, 1)
for i in range(self.n_points):
grid_init[:, :, i, :] *= i + 1
with torch.no_grad():
self.sampling_offsets.bias = nn.Parameter(grid_init.view(-1))
constant_(self.attention_weights.weight.data, 0.)
constant_(self.attention_weights.bias.data, 0.)
xavier_uniform_(self.value_proj.weight.data)
constant_(self.value_proj.bias.data, 0.)
xavier_uniform_(self.output_proj.weight.data)
constant_(self.output_proj.bias.data, 0.)
def forward(self, query, reference_points, input_flatten, input_spatial_shapes, input_level_start_index, input_padding_mask=None):
"""
:param query (N, Length_{query}, C)
:param reference_points (N, Length_{query}, n_levels, 2), range in [0, 1], top-left (0,0), bottom-right (1, 1), including padding area
or (N, Length_{query}, n_levels, 4), add additional (w, h) to form reference boxes
:param input_flatten (N, \sum_{l=0}^{L-1} H_l \cdot W_l, C)
:param input_spatial_shapes (n_levels, 2), [(H_0, W_0), (H_1, W_1), ..., (H_{L-1}, W_{L-1})]
:param input_level_start_index (n_levels, ), [0, H_0*W_0, H_0*W_0+H_1*W_1, H_0*W_0+H_1*W_1+H_2*W_2, ..., H_0*W_0+H_1*W_1+...+H_{L-1}*W_{L-1}]
:param input_padding_mask (N, \sum_{l=0}^{L-1} H_l \cdot W_l), True for padding elements, False for non-padding elements
:return output (N, Length_{query}, C)
"""
N, Len_q, _ = query.shape
N, Len_in, _ = input_flatten.shape
assert (input_spatial_shapes[:, 0] * input_spatial_shapes[:, 1]).sum() == Len_in
value = self.value_proj(input_flatten)
if input_padding_mask is not None:
value.masked_fill_(input_padding_mask[..., None], float(0))
value = value.view(N, Len_in, self.n_heads, self.d_model // self.n_heads)
sampling_offsets = self.sampling_offsets(query).view(N, Len_q, self.n_heads, self.n_levels, self.n_points, 2)
attention_weights = self.attention_weights(query).view(N, Len_q, self.n_heads, self.n_levels * self.n_points)
if self.sigmoid_attn:
attention_weights = attention_weights.sigmoid().view(N, Len_q, self.n_heads, self.n_levels, self.n_points)
else:
attention_weights = F.softmax(attention_weights, -1).view(N, Len_q, self.n_heads, self.n_levels, self.n_points)
# N, Len_q, n_heads, n_levels, n_points, 2
if reference_points.shape[-1] == 2:
sampling_locations = reference_points[:, :, None, :, None, :] \
+ sampling_offsets / input_spatial_shapes[None, None, None, :, None, (1, 0)]
elif reference_points.shape[-1] == 4:
sampling_locations = reference_points[:, :, None, :, None, :2] \
+ sampling_offsets / self.n_points * reference_points[:, :, None, :, None, 2:] * 0.5
else:
raise ValueError(
'Last dim of reference_points must be 2 or 4, but get {} instead.'.format(reference_points.shape[-1]))
output = MSDeformAttnFunction.apply(
value, input_spatial_shapes, input_level_start_index, sampling_locations, attention_weights, self.im2col_step)
output = self.output_proj(output)
return output
|