1. GENet
论文：https://arxiv.org/pdf/1904.11492.pdf
简单的低级特征聚合方法，如Global-Avg-Pooling的方式已被SENet证明是有效的方式，且一系列Bag-of-Visual-words模型也表明：用汇集局部区域所得的局部描述子，来组建成新的表示，这种方法是有效的。 故GENet针对如何从特征图中提取出好的feature context，再用于特征图间重要程度的调控进行了研究（基于SENet）
2. GENet加入yolov5
2.1 加入common.py中：
代码语言：javascript复制###################### GENet GatherExcite #### start by AI&CV ###############################
import math, torch
from torch import nn as nn
import torch.nn.functional as F
from timm.models.layers.create_act import create_act_layer, get_act_layer
from timm.models.layers.create_conv2d import create_conv2d
from timm.models.layers.helpers import make_divisible
from timm.models.layers.mlp import ConvMlp
class GatherExcite(nn.Module):
def __init__(
self, channels, feat_size=None, extra_params=False, extent=0, use_mlp=True,
rd_ratio=1./16, rd_channels=None, rd_divisor=1, add_maxpool=False,
act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d, gate_layer='sigmoid'):
super(GatherExcite, self).__init__()
self.add_maxpool = add_maxpool
act_layer = get_act_layer(act_layer)
self.extent = extent
if extra_params:
self.gather = nn.Sequential()
if extent == 0:
assert feat_size is not None, 'spatial feature size must be specified for global extent w/ params'
self.gather.add_module(
'conv1', create_conv2d(channels, channels, kernel_size=feat_size, stride=1, depthwise=True))
if norm_layer:
self.gather.add_module(f'norm1', nn.BatchNorm2d(channels))
else:
assert extent % 2 == 0
num_conv = int(math.log2(extent))
for i in range(num_conv):
self.gather.add_module(
f'conv{i 1}',
create_conv2d(channels, channels, kernel_size=3, stride=2, depthwise=True))
if norm_layer:
self.gather.add_module(f'norm{i 1}', nn.BatchNorm2d(channels))
if i != num_conv - 1:
self.gather.add_module(f'act{i 1}', act_layer(inplace=True))
else:
self.gather = None
if self.extent == 0:
self.gk = 0
self.gs = 0
else:
assert extent % 2 == 0
self.gk = self.extent * 2 - 1
self.gs = self.extent
if not rd_channels:
rd_channels = make_divisible(channels * rd_ratio, rd_divisor, round_limit=0.)
self.mlp = ConvMlp(channels, rd_channels, act_layer=act_layer) if use_mlp else nn.Identity()
self.gate = create_act_layer(gate_layer)
def forward(self, x):
size = x.shape[-2:]
if self.gather is not None:
x_ge = self.gather(x)
else:
if self.extent == 0:
# global extent
x_ge = x.mean(dim=(2, 3), keepdims=True)
if self.add_maxpool:
# experimental codepath, may remove or change
x_ge = 0.5 * x_ge 0.5 * x.amax((2, 3), keepdim=True)
else:
x_ge = F.avg_pool2d(
x, kernel_size=self.gk, stride=self.gs, padding=self.gk // 2, count_include_pad=False)
if self.add_maxpool:
# experimental codepath, may remove or change
x_ge = 0.5 * x_ge 0.5 * F.max_pool2d(x, kernel_size=self.gk, stride=self.gs, padding=self.gk // 2)
x_ge = self.mlp(x_ge)
if x_ge.shape[-1] != 1 or x_ge.shape[-2] != 1:
x_ge = F.interpolate(x_ge, size=size)
return x * self.gate(x_ge)
###################### GENet GatherExcite #### end by AI&CV ###############################2.2 yolov5s_GEnet_GatherExcite.yaml
代码语言：javascript复制# YOLOv5
