Spaces:
Sleeping
Sleeping
File size: 9,838 Bytes
186701e |
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 |
# Copyright (c) Tencent Inc. All rights reserved.
import copy
from typing import List, Union
import torch
import torch.nn as nn
from torch import Tensor
from mmdet.utils import ConfigType, OptMultiConfig
from mmyolo.registry import MODELS
from mmyolo.models.utils import make_divisible, make_round
from mmyolo.models.necks.yolov8_pafpn import YOLOv8PAFPN
@MODELS.register_module()
class YOLOWorldPAFPN(YOLOv8PAFPN):
"""Path Aggregation Network used in YOLO World
Following YOLOv8 PAFPN, including text to image fusion
"""
def __init__(self,
in_channels: List[int],
out_channels: Union[List[int], int],
guide_channels: int,
embed_channels: List[int],
num_heads: List[int],
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
num_csp_blocks: int = 3,
freeze_all: bool = False,
block_cfg: ConfigType = dict(type='CSPLayerWithTwoConv'),
norm_cfg: ConfigType = dict(type='BN',
momentum=0.03,
eps=0.001),
act_cfg: ConfigType = dict(type='SiLU', inplace=True),
init_cfg: OptMultiConfig = None) -> None:
self.guide_channels = guide_channels
self.embed_channels = embed_channels
self.num_heads = num_heads
self.block_cfg = block_cfg
super().__init__(in_channels=in_channels,
out_channels=out_channels,
deepen_factor=deepen_factor,
widen_factor=widen_factor,
num_csp_blocks=num_csp_blocks,
freeze_all=freeze_all,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
init_cfg=init_cfg)
def build_top_down_layer(self, idx: int) -> nn.Module:
"""build top down layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The top down layer.
"""
block_cfg = copy.deepcopy(self.block_cfg)
block_cfg.update(
dict(in_channels=make_divisible(
(self.in_channels[idx - 1] + self.in_channels[idx]),
self.widen_factor),
out_channels=make_divisible(self.out_channels[idx - 1],
self.widen_factor),
guide_channels=self.guide_channels,
embed_channels=make_round(self.embed_channels[idx - 1],
self.widen_factor),
num_heads=make_round(self.num_heads[idx - 1],
self.widen_factor),
num_blocks=make_round(self.num_csp_blocks,
self.deepen_factor),
add_identity=False,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg))
return MODELS.build(block_cfg)
def build_bottom_up_layer(self, idx: int) -> nn.Module:
"""build bottom up layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The bottom up layer.
"""
block_cfg = copy.deepcopy(self.block_cfg)
block_cfg.update(
dict(in_channels=make_divisible(
(self.out_channels[idx] + self.out_channels[idx + 1]),
self.widen_factor),
out_channels=make_divisible(self.out_channels[idx + 1],
self.widen_factor),
guide_channels=self.guide_channels,
embed_channels=make_round(self.embed_channels[idx + 1],
self.widen_factor),
num_heads=make_round(self.num_heads[idx + 1],
self.widen_factor),
num_blocks=make_round(self.num_csp_blocks,
self.deepen_factor),
add_identity=False,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg))
return MODELS.build(block_cfg)
def forward(self, img_feats: List[Tensor], txt_feats: Tensor) -> tuple:
"""Forward function.
including multi-level image features, text features: BxLxD
"""
assert len(img_feats) == len(self.in_channels)
# reduce layers
reduce_outs = []
for idx in range(len(self.in_channels)):
reduce_outs.append(self.reduce_layers[idx](img_feats[idx]))
# top-down path
inner_outs = [reduce_outs[-1]]
for idx in range(len(self.in_channels) - 1, 0, -1):
feat_high = inner_outs[0]
feat_low = reduce_outs[idx - 1]
upsample_feat = self.upsample_layers[len(self.in_channels) - 1 -
idx](feat_high)
if self.upsample_feats_cat_first:
top_down_layer_inputs = torch.cat([upsample_feat, feat_low], 1)
else:
top_down_layer_inputs = torch.cat([feat_low, upsample_feat], 1)
inner_out = self.top_down_layers[len(self.in_channels) - 1 - idx](
top_down_layer_inputs, txt_feats)
inner_outs.insert(0, inner_out)
# bottom-up path
outs = [inner_outs[0]]
for idx in range(len(self.in_channels) - 1):
feat_low = outs[-1]
feat_high = inner_outs[idx + 1]
downsample_feat = self.downsample_layers[idx](feat_low)
out = self.bottom_up_layers[idx](torch.cat(
[downsample_feat, feat_high], 1), txt_feats)
outs.append(out)
# out_layers
results = []
for idx in range(len(self.in_channels)):
results.append(self.out_layers[idx](outs[idx]))
return tuple(results)
@MODELS.register_module()
class YOLOWolrdDualPAFPN(YOLOWorldPAFPN):
"""Path Aggregation Network used in YOLO World v8."""
def __init__(self,
in_channels: List[int],
out_channels: Union[List[int], int],
guide_channels: int,
embed_channels: List[int],
num_heads: List[int],
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
num_csp_blocks: int = 3,
freeze_all: bool = False,
text_enhancder: ConfigType = dict(
type='ImagePoolingAttentionModule',
embed_channels=256,
num_heads=8,
pool_size=3),
block_cfg: ConfigType = dict(type='CSPLayerWithTwoConv'),
norm_cfg: ConfigType = dict(type='BN',
momentum=0.03,
eps=0.001),
act_cfg: ConfigType = dict(type='SiLU', inplace=True),
init_cfg: OptMultiConfig = None) -> None:
super().__init__(in_channels=in_channels,
out_channels=out_channels,
guide_channels=guide_channels,
embed_channels=embed_channels,
num_heads=num_heads,
deepen_factor=deepen_factor,
widen_factor=widen_factor,
num_csp_blocks=num_csp_blocks,
freeze_all=freeze_all,
block_cfg=block_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
init_cfg=init_cfg)
text_enhancder.update(
dict(
image_channels=[int(x * widen_factor) for x in out_channels],
text_channels=guide_channels,
num_feats=len(out_channels),
))
print(text_enhancder)
self.text_enhancer = MODELS.build(text_enhancder)
def forward(self, img_feats: List[Tensor], txt_feats: Tensor) -> tuple:
"""Forward function."""
assert len(img_feats) == len(self.in_channels)
# reduce layers
reduce_outs = []
for idx in range(len(self.in_channels)):
reduce_outs.append(self.reduce_layers[idx](img_feats[idx]))
# top-down path
inner_outs = [reduce_outs[-1]]
for idx in range(len(self.in_channels) - 1, 0, -1):
feat_high = inner_outs[0]
feat_low = reduce_outs[idx - 1]
upsample_feat = self.upsample_layers[len(self.in_channels) - 1 -
idx](feat_high)
if self.upsample_feats_cat_first:
top_down_layer_inputs = torch.cat([upsample_feat, feat_low], 1)
else:
top_down_layer_inputs = torch.cat([feat_low, upsample_feat], 1)
inner_out = self.top_down_layers[len(self.in_channels) - 1 - idx](
top_down_layer_inputs, txt_feats)
inner_outs.insert(0, inner_out)
txt_feats = self.text_enhancer(txt_feats, inner_outs)
# bottom-up path
outs = [inner_outs[0]]
for idx in range(len(self.in_channels) - 1):
feat_low = outs[-1]
feat_high = inner_outs[idx + 1]
downsample_feat = self.downsample_layers[idx](feat_low)
out = self.bottom_up_layers[idx](torch.cat(
[downsample_feat, feat_high], 1), txt_feats)
outs.append(out)
# out_layers
results = []
for idx in range(len(self.in_channels)):
results.append(self.out_layers[idx](outs[idx]))
return tuple(results)
|