Spaces:
Runtime error
Runtime error
File size: 7,245 Bytes
3b96cb1 |
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 |
# Copyright (c) OpenMMLab. All rights reserved.
from typing import Dict, List
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.cnn import ConvModule
from mmengine.model import BaseModule, ModuleList, Sequential
from torch import Tensor
class DAPPM(BaseModule):
"""DAPPM module in `DDRNet <https://arxiv.org/abs/2101.06085>`_.
Args:
in_channels (int): Input channels.
branch_channels (int): Branch channels.
out_channels (int): Output channels.
num_scales (int): Number of scales.
kernel_sizes (list[int]): Kernel sizes of each scale.
strides (list[int]): Strides of each scale.
paddings (list[int]): Paddings of each scale.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
act_cfg (dict): Config dict for activation layer in ConvModule.
Default: dict(type='ReLU', inplace=True).
conv_cfg (dict): Config dict for convolution layer in ConvModule.
Default: dict(order=('norm', 'act', 'conv'), bias=False).
upsample_mode (str): Upsample mode. Default: 'bilinear'.
"""
def __init__(self,
in_channels: int,
branch_channels: int,
out_channels: int,
num_scales: int,
kernel_sizes: List[int] = [5, 9, 17],
strides: List[int] = [2, 4, 8],
paddings: List[int] = [2, 4, 8],
norm_cfg: Dict = dict(type='BN', momentum=0.1),
act_cfg: Dict = dict(type='ReLU', inplace=True),
conv_cfg: Dict = dict(
order=('norm', 'act', 'conv'), bias=False),
upsample_mode: str = 'bilinear'):
super().__init__()
self.num_scales = num_scales
self.unsample_mode = upsample_mode
self.in_channels = in_channels
self.branch_channels = branch_channels
self.out_channels = out_channels
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.conv_cfg = conv_cfg
self.scales = ModuleList([
ConvModule(
in_channels,
branch_channels,
kernel_size=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg)
])
for i in range(1, num_scales - 1):
self.scales.append(
Sequential(*[
nn.AvgPool2d(
kernel_size=kernel_sizes[i - 1],
stride=strides[i - 1],
padding=paddings[i - 1]),
ConvModule(
in_channels,
branch_channels,
kernel_size=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg)
]))
self.scales.append(
Sequential(*[
nn.AdaptiveAvgPool2d((1, 1)),
ConvModule(
in_channels,
branch_channels,
kernel_size=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg)
]))
self.processes = ModuleList()
for i in range(num_scales - 1):
self.processes.append(
ConvModule(
branch_channels,
branch_channels,
kernel_size=3,
padding=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg))
self.compression = ConvModule(
branch_channels * num_scales,
out_channels,
kernel_size=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg)
self.shortcut = ConvModule(
in_channels,
out_channels,
kernel_size=1,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
**conv_cfg)
def forward(self, inputs: Tensor):
feats = []
feats.append(self.scales[0](inputs))
for i in range(1, self.num_scales):
feat_up = F.interpolate(
self.scales[i](inputs),
size=inputs.shape[2:],
mode=self.unsample_mode)
feats.append(self.processes[i - 1](feat_up + feats[i - 1]))
return self.compression(torch.cat(feats,
dim=1)) + self.shortcut(inputs)
class PAPPM(DAPPM):
"""PAPPM module in `PIDNet <https://arxiv.org/abs/2206.02066>`_.
Args:
in_channels (int): Input channels.
branch_channels (int): Branch channels.
out_channels (int): Output channels.
num_scales (int): Number of scales.
kernel_sizes (list[int]): Kernel sizes of each scale.
strides (list[int]): Strides of each scale.
paddings (list[int]): Paddings of each scale.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN', momentum=0.1).
act_cfg (dict): Config dict for activation layer in ConvModule.
Default: dict(type='ReLU', inplace=True).
conv_cfg (dict): Config dict for convolution layer in ConvModule.
Default: dict(order=('norm', 'act', 'conv'), bias=False).
upsample_mode (str): Upsample mode. Default: 'bilinear'.
"""
def __init__(self,
in_channels: int,
branch_channels: int,
out_channels: int,
num_scales: int,
kernel_sizes: List[int] = [5, 9, 17],
strides: List[int] = [2, 4, 8],
paddings: List[int] = [2, 4, 8],
norm_cfg: Dict = dict(type='BN', momentum=0.1),
act_cfg: Dict = dict(type='ReLU', inplace=True),
conv_cfg: Dict = dict(
order=('norm', 'act', 'conv'), bias=False),
upsample_mode: str = 'bilinear'):
super().__init__(in_channels, branch_channels, out_channels,
num_scales, kernel_sizes, strides, paddings, norm_cfg,
act_cfg, conv_cfg, upsample_mode)
self.processes = ConvModule(
self.branch_channels * (self.num_scales - 1),
self.branch_channels * (self.num_scales - 1),
kernel_size=3,
padding=1,
groups=self.num_scales - 1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg,
**self.conv_cfg)
def forward(self, inputs: Tensor):
x_ = self.scales[0](inputs)
feats = []
for i in range(1, self.num_scales):
feat_up = F.interpolate(
self.scales[i](inputs),
size=inputs.shape[2:],
mode=self.unsample_mode,
align_corners=False)
feats.append(feat_up + x_)
scale_out = self.processes(torch.cat(feats, dim=1))
return self.compression(torch.cat([x_, scale_out],
dim=1)) + self.shortcut(inputs)
|