YOLOv8改进
第三章 使用C2f-Faster-EMA替换C2f.(C2f-Faster-EMA推荐可以放在主干上,Neck和head部分可以选择C2f-Faster)
一、yolov8-C2f-Faster-EMA模型
1.yolov8-C2f-Faster-EMA模型结构
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f_Faster_EMA, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f_Faster_EMA, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f_Faster_EMA, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f_Faster_EMA, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f_Faster_EMA, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f_Faster_EMA, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f_Faster_EMA, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f_Faster_EMA, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
2.C2f-Faster-EMA代码
class Faster_Block_EMA(nn.Module):
def __init__(self,
inc,
dim,
n_div=4,
mlp_ratio=2,
drop_path=0.1,
layer_scale_init_value=0.0,
pconv_fw_type='split_cat'
):
super().__init__()
self.dim = dim
self.mlp_ratio = mlp_ratio
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.n_div = n_div
mlp_hidden_dim = int(dim * mlp_ratio)
mlp_layer = [
Conv(dim, mlp_hidden_dim, 1),
nn.Conv2d(mlp_hidden_dim, dim, 1, bias=False)
]
self.mlp = nn.Sequential(*mlp_layer)
self.spatial_mixing = Partial_conv3(
dim,
n_div,
pconv_fw_type
)
self.attention = EMA(dim)
self.adjust_channel = None
if inc != dim:
self.adjust_channel = Conv(inc, dim, 1)
if layer_scale_init_value > 0:
self.layer_scale = nn.Parameter(layer_scale_init_value * torch.ones((dim)), requires_grad=True)
self.forward = self.forward_layer_scale
else:
self.forward = self.forward
def forward(self, x):
if self.adjust_channel is not None:
x = self.adjust_channel(x)
shortcut = x
x = self.spatial_mixing(x)
x = shortcut + self.attention(self.drop_path(self.mlp(x)))
return x
def forward_layer_scale(self, x):
shortcut = x
x = self.spatial_mixing(x)
x = shortcut + self.drop_path(self.layer_scale.unsqueeze(-1).unsqueeze(-1) * self.mlp(x))
return x
class C3_Faster_EMA(C3):
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
self.m = nn.Sequential(*(Faster_Block_EMA(c_, c_) for _ in range(n)))
class C2f_Faster_EMA(C2f):
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
self.m = nn.ModuleList(Faster_Block_EMA(self.c, self.c) for _ in range(n))
二、添加方式
1.将上文中C2f-Faster-EMA代码添加ultralytics/nn/modules/block.py中
2.在block.py的顶部注册模块名.
'C2f_Faster_EMA'
3.在ultralytics/nn/modules/__init__.py中注册模块名
C2f_Faster_EMA 'C2f_Faster_EMA'
4.在ultralytics/nn/tasks.py顶部注册模块名
C2f_Faster_EMA
5.在ultralytics/nn/tasks.py中的def parse_model添加
C2f_Faster_EMA