Spaces:
Running
on
Zero
Running
on
Zero
File size: 8,161 Bytes
e85fecb |
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 |
"""
Copied from RT-DETR (https://github.com/lyuwenyu/RT-DETR)
Copyright(c) 2023 lyuwenyu. All Rights Reserved.
"""
from collections import OrderedDict
import torch
import torch.nn as nn
import torch.nn.functional as F
from ...core import register
from .common import FrozenBatchNorm2d, get_activation
__all__ = ["PResNet"]
ResNet_cfg = {
18: [2, 2, 2, 2],
34: [3, 4, 6, 3],
50: [3, 4, 6, 3],
101: [3, 4, 23, 3],
# 152: [3, 8, 36, 3],
}
donwload_url = {
18: "https://github.com/lyuwenyu/storage/releases/download/v0.1/ResNet18_vd_pretrained_from_paddle.pth",
34: "https://github.com/lyuwenyu/storage/releases/download/v0.1/ResNet34_vd_pretrained_from_paddle.pth",
50: "https://github.com/lyuwenyu/storage/releases/download/v0.1/ResNet50_vd_ssld_v2_pretrained_from_paddle.pth",
101: "https://github.com/lyuwenyu/storage/releases/download/v0.1/ResNet101_vd_ssld_pretrained_from_paddle.pth",
}
class ConvNormLayer(nn.Module):
def __init__(self, ch_in, ch_out, kernel_size, stride, padding=None, bias=False, act=None):
super().__init__()
self.conv = nn.Conv2d(
ch_in,
ch_out,
kernel_size,
stride,
padding=(kernel_size - 1) // 2 if padding is None else padding,
bias=bias,
)
self.norm = nn.BatchNorm2d(ch_out)
self.act = get_activation(act)
def forward(self, x):
return self.act(self.norm(self.conv(x)))
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, ch_in, ch_out, stride, shortcut, act="relu", variant="b"):
super().__init__()
self.shortcut = shortcut
if not shortcut:
if variant == "d" and stride == 2:
self.short = nn.Sequential(
OrderedDict(
[
("pool", nn.AvgPool2d(2, 2, 0, ceil_mode=True)),
("conv", ConvNormLayer(ch_in, ch_out, 1, 1)),
]
)
)
else:
self.short = ConvNormLayer(ch_in, ch_out, 1, stride)
self.branch2a = ConvNormLayer(ch_in, ch_out, 3, stride, act=act)
self.branch2b = ConvNormLayer(ch_out, ch_out, 3, 1, act=None)
self.act = nn.Identity() if act is None else get_activation(act)
def forward(self, x):
out = self.branch2a(x)
out = self.branch2b(out)
if self.shortcut:
short = x
else:
short = self.short(x)
out = out + short
out = self.act(out)
return out
class BottleNeck(nn.Module):
expansion = 4
def __init__(self, ch_in, ch_out, stride, shortcut, act="relu", variant="b"):
super().__init__()
if variant == "a":
stride1, stride2 = stride, 1
else:
stride1, stride2 = 1, stride
width = ch_out
self.branch2a = ConvNormLayer(ch_in, width, 1, stride1, act=act)
self.branch2b = ConvNormLayer(width, width, 3, stride2, act=act)
self.branch2c = ConvNormLayer(width, ch_out * self.expansion, 1, 1)
self.shortcut = shortcut
if not shortcut:
if variant == "d" and stride == 2:
self.short = nn.Sequential(
OrderedDict(
[
("pool", nn.AvgPool2d(2, 2, 0, ceil_mode=True)),
("conv", ConvNormLayer(ch_in, ch_out * self.expansion, 1, 1)),
]
)
)
else:
self.short = ConvNormLayer(ch_in, ch_out * self.expansion, 1, stride)
self.act = nn.Identity() if act is None else get_activation(act)
def forward(self, x):
out = self.branch2a(x)
out = self.branch2b(out)
out = self.branch2c(out)
if self.shortcut:
short = x
else:
short = self.short(x)
out = out + short
out = self.act(out)
return out
class Blocks(nn.Module):
def __init__(self, block, ch_in, ch_out, count, stage_num, act="relu", variant="b"):
super().__init__()
self.blocks = nn.ModuleList()
for i in range(count):
self.blocks.append(
block(
ch_in,
ch_out,
stride=2 if i == 0 and stage_num != 2 else 1,
shortcut=False if i == 0 else True,
variant=variant,
act=act,
)
)
if i == 0:
ch_in = ch_out * block.expansion
def forward(self, x):
out = x
for block in self.blocks:
out = block(out)
return out
@register()
class PResNet(nn.Module):
def __init__(
self,
depth,
variant="d",
num_stages=4,
return_idx=[0, 1, 2, 3],
act="relu",
freeze_at=-1,
freeze_norm=True,
pretrained=False,
):
super().__init__()
block_nums = ResNet_cfg[depth]
ch_in = 64
if variant in ["c", "d"]:
conv_def = [
[3, ch_in // 2, 3, 2, "conv1_1"],
[ch_in // 2, ch_in // 2, 3, 1, "conv1_2"],
[ch_in // 2, ch_in, 3, 1, "conv1_3"],
]
else:
conv_def = [[3, ch_in, 7, 2, "conv1_1"]]
self.conv1 = nn.Sequential(
OrderedDict(
[
(name, ConvNormLayer(cin, cout, k, s, act=act))
for cin, cout, k, s, name in conv_def
]
)
)
ch_out_list = [64, 128, 256, 512]
block = BottleNeck if depth >= 50 else BasicBlock
_out_channels = [block.expansion * v for v in ch_out_list]
_out_strides = [4, 8, 16, 32]
self.res_layers = nn.ModuleList()
for i in range(num_stages):
stage_num = i + 2
self.res_layers.append(
Blocks(
block, ch_in, ch_out_list[i], block_nums[i], stage_num, act=act, variant=variant
)
)
ch_in = _out_channels[i]
self.return_idx = return_idx
self.out_channels = [_out_channels[_i] for _i in return_idx]
self.out_strides = [_out_strides[_i] for _i in return_idx]
if freeze_at >= 0:
self._freeze_parameters(self.conv1)
for i in range(min(freeze_at, num_stages)):
self._freeze_parameters(self.res_layers[i])
if freeze_norm:
self._freeze_norm(self)
if pretrained:
if isinstance(pretrained, bool) or "http" in pretrained:
state = torch.hub.load_state_dict_from_url(
donwload_url[depth], map_location="cpu", model_dir="weight"
)
else:
state = torch.load(pretrained, map_location="cpu")
self.load_state_dict(state)
print(f"Load PResNet{depth} state_dict")
def _freeze_parameters(self, m: nn.Module):
for p in m.parameters():
p.requires_grad = False
def _freeze_norm(self, m: nn.Module):
if isinstance(m, nn.BatchNorm2d):
m = FrozenBatchNorm2d(m.num_features)
else:
for name, child in m.named_children():
_child = self._freeze_norm(child)
if _child is not child:
setattr(m, name, _child)
return m
def forward(self, x):
conv1 = self.conv1(x)
x = F.max_pool2d(conv1, kernel_size=3, stride=2, padding=1)
outs = []
for idx, stage in enumerate(self.res_layers):
x = stage(x)
if idx in self.return_idx:
outs.append(x)
return outs
|