File size: 6,718 Bytes
c9019cd |
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 |
import torch.nn as nn
from mmcv.cnn import ConvModule
from mmcv.runner import BaseModule
from ..builder import BACKBONES
from ..utils import ResLayer
from .resnet import BasicBlock
class HourglassModule(BaseModule):
"""Hourglass Module for HourglassNet backbone.
Generate module recursively and use BasicBlock as the base unit.
Args:
depth (int): Depth of current HourglassModule.
stage_channels (list[int]): Feature channels of sub-modules in current
and follow-up HourglassModule.
stage_blocks (list[int]): Number of sub-modules stacked in current and
follow-up HourglassModule.
norm_cfg (dict): Dictionary to construct and config norm layer.
init_cfg (dict or list[dict], optional): Initialization config dict.
Default: None
"""
def __init__(self,
depth,
stage_channels,
stage_blocks,
norm_cfg=dict(type='BN', requires_grad=True),
init_cfg=None):
super(HourglassModule, self).__init__(init_cfg)
self.depth = depth
cur_block = stage_blocks[0]
next_block = stage_blocks[1]
cur_channel = stage_channels[0]
next_channel = stage_channels[1]
self.up1 = ResLayer(
BasicBlock, cur_channel, cur_channel, cur_block, norm_cfg=norm_cfg)
self.low1 = ResLayer(
BasicBlock,
cur_channel,
next_channel,
cur_block,
stride=2,
norm_cfg=norm_cfg)
if self.depth > 1:
self.low2 = HourglassModule(depth - 1, stage_channels[1:],
stage_blocks[1:])
else:
self.low2 = ResLayer(
BasicBlock,
next_channel,
next_channel,
next_block,
norm_cfg=norm_cfg)
self.low3 = ResLayer(
BasicBlock,
next_channel,
cur_channel,
cur_block,
norm_cfg=norm_cfg,
downsample_first=False)
self.up2 = nn.Upsample(scale_factor=2)
def forward(self, x):
"""Forward function."""
up1 = self.up1(x)
low1 = self.low1(x)
low2 = self.low2(low1)
low3 = self.low3(low2)
up2 = self.up2(low3)
return up1 + up2
@BACKBONES.register_module()
class HourglassNet(BaseModule):
"""HourglassNet backbone.
Stacked Hourglass Networks for Human Pose Estimation.
More details can be found in the `paper
<https://arxiv.org/abs/1603.06937>`_ .
Args:
downsample_times (int): Downsample times in a HourglassModule.
num_stacks (int): Number of HourglassModule modules stacked,
1 for Hourglass-52, 2 for Hourglass-104.
stage_channels (list[int]): Feature channel of each sub-module in a
HourglassModule.
stage_blocks (list[int]): Number of sub-modules stacked in a
HourglassModule.
feat_channel (int): Feature channel of conv after a HourglassModule.
norm_cfg (dict): Dictionary to construct and config norm layer.
pretrained (str, optional): model pretrained path. Default: None
init_cfg (dict or list[dict], optional): Initialization config dict.
Default: None
Example:
>>> from mmdet.models import HourglassNet
>>> import torch
>>> self = HourglassNet()
>>> self.eval()
>>> inputs = torch.rand(1, 3, 511, 511)
>>> level_outputs = self.forward(inputs)
>>> for level_output in level_outputs:
... print(tuple(level_output.shape))
(1, 256, 128, 128)
(1, 256, 128, 128)
"""
def __init__(self,
downsample_times=5,
num_stacks=2,
stage_channels=(256, 256, 384, 384, 384, 512),
stage_blocks=(2, 2, 2, 2, 2, 4),
feat_channel=256,
norm_cfg=dict(type='BN', requires_grad=True),
pretrained=None,
init_cfg=None):
assert init_cfg is None, 'To prevent abnormal initialization ' \
'behavior, init_cfg is not allowed to be set'
super(HourglassNet, self).__init__(init_cfg)
self.num_stacks = num_stacks
assert self.num_stacks >= 1
assert len(stage_channels) == len(stage_blocks)
assert len(stage_channels) > downsample_times
cur_channel = stage_channels[0]
self.stem = nn.Sequential(
ConvModule(3, 128, 7, padding=3, stride=2, norm_cfg=norm_cfg),
ResLayer(BasicBlock, 128, 256, 1, stride=2, norm_cfg=norm_cfg))
self.hourglass_modules = nn.ModuleList([
HourglassModule(downsample_times, stage_channels, stage_blocks)
for _ in range(num_stacks)
])
self.inters = ResLayer(
BasicBlock,
cur_channel,
cur_channel,
num_stacks - 1,
norm_cfg=norm_cfg)
self.conv1x1s = nn.ModuleList([
ConvModule(
cur_channel, cur_channel, 1, norm_cfg=norm_cfg, act_cfg=None)
for _ in range(num_stacks - 1)
])
self.out_convs = nn.ModuleList([
ConvModule(
cur_channel, feat_channel, 3, padding=1, norm_cfg=norm_cfg)
for _ in range(num_stacks)
])
self.remap_convs = nn.ModuleList([
ConvModule(
feat_channel, cur_channel, 1, norm_cfg=norm_cfg, act_cfg=None)
for _ in range(num_stacks - 1)
])
self.relu = nn.ReLU(inplace=True)
def init_weights(self):
"""Init module weights."""
# Training Centripetal Model needs to reset parameters for Conv2d
super(HourglassNet, self).init_weights()
for m in self.modules():
if isinstance(m, nn.Conv2d):
m.reset_parameters()
def forward(self, x):
"""Forward function."""
inter_feat = self.stem(x)
out_feats = []
for ind in range(self.num_stacks):
single_hourglass = self.hourglass_modules[ind]
out_conv = self.out_convs[ind]
hourglass_feat = single_hourglass(inter_feat)
out_feat = out_conv(hourglass_feat)
out_feats.append(out_feat)
if ind < self.num_stacks - 1:
inter_feat = self.conv1x1s[ind](
inter_feat) + self.remap_convs[ind](
out_feat)
inter_feat = self.inters[ind](self.relu(inter_feat))
return out_feats
|