YOLOv8改进------------SPFF-LSKA
YOLOv8改进------------SPFF-LSKA
- 1、LSAK.py代码
- 2、添加YAML文件yolov8_SPPF_LSKA.yaml
- 3、添加SPPF_LSKA代码
- 4、ultralytics/nn/modules/__init__.py注册模块
- 5、ultralytics/nn/tasks.py注册模块
- 6、导入yaml文件训练
1、LSAK.py代码
论文
代码
LSKA.py添加到ultralytics/nn/modules中
import torch
import torch.nn as nn
import torch.nn.functional as F
from functools import partial
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
from timm.models.registry import register_model
from timm.models.vision_transformer import _cfg
import math
class Mlp(nn.Module):
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
self.dwconv = DWConv(hidden_features)
self.act = act_layer()
self.fc2 = nn.Conv2d(hidden_features, out_features, 1)
self.drop = nn.Dropout(drop)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
elif isinstance(m, nn.Conv2d):
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
fan_out //= m.groups
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
if m.bias is not None:
m.bias.data.zero_()
def forward(self, x):
x = self.fc1(x)
x = self.dwconv(x)
x = self.act(x)
x = self.drop(x)
x = self.fc2(x)
x = self.drop(x)
return x
class LSKA(nn.Module):
def __init__(self, dim, k_size):
super().__init__()
self.k_size = k_size
if k_size == 7:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,(3-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=((3-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,2), groups=dim, dilation=2)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=(2,0), groups=dim, dilation=2)
elif k_size == 11:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 3), stride=(1,1), padding=(0,(3-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(3, 1), stride=(1,1), padding=((3-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,4), groups=dim, dilation=2)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=(4,0), groups=dim, dilation=2)
elif k_size == 23:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 7), stride=(1,1), padding=(0,9), groups=dim, dilation=3)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(7, 1), stride=(1,1), padding=(9,0), groups=dim, dilation=3)
elif k_size == 35:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 11), stride=(1,1), padding=(0,15), groups=dim, dilation=3)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(11, 1), stride=(1,1), padding=(15,0), groups=dim, dilation=3)
elif k_size == 41:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 13), stride=(1,1), padding=(0,18), groups=dim, dilation=3)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(13, 1), stride=(1,1), padding=(18,0), groups=dim, dilation=3)
elif k_size == 53:
self.conv0h = nn.Conv2d(dim, dim, kernel_size=(1, 5), stride=(1,1), padding=(0,(5-1)//2), groups=dim)
self.conv0v = nn.Conv2d(dim, dim, kernel_size=(5, 1), stride=(1,1), padding=((5-1)//2,0), groups=dim)
self.conv_spatial_h = nn.Conv2d(dim, dim, kernel_size=(1, 17), stride=(1,1), padding=(0,24), groups=dim, dilation=3)
self.conv_spatial_v = nn.Conv2d(dim, dim, kernel_size=(17, 1), stride=(1,1), padding=(24,0), groups=dim, dilation=3)
self.conv1 = nn.Conv2d(dim, dim, 1)
def forward(self, x):
u = x.clone()
attn = self.conv0h(x)
attn = self.conv0v(attn)
attn = self.conv_spatial_h(attn)
attn = self.conv_spatial_v(attn)
attn = self.conv1(attn)
return u * attn
class Attention(nn.Module):
def __init__(self, d_model, k_size):
super().__init__()
self.proj_1 = nn.Conv2d(d_model, d_model, 1)
self.activation = nn.GELU()
self.spatial_gating_unit = LSKA(d_model, k_size)
self.proj_2 = nn.Conv2d(d_model, d_model, 1)
def forward(self, x):
shorcut = x.clone()
x = self.proj_1(x)
x = self.activation(x)
x = self.spatial_gating_unit(x)
x = self.proj_2(x)
x = x + shorcut
return x
class Block(nn.Module):
def __init__(self, dim, k_size, mlp_ratio=4., drop=0.,drop_path=0., act_layer=nn.GELU):
super().__init__()
self.norm1 = nn.BatchNorm2d(dim)
self.attn = Attention(dim, k_size)
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = nn.BatchNorm2d(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
layer_scale_init_value = 1e-2
self.layer_scale_1 = nn.Parameter(
layer_scale_init_value * torch.ones((dim)), requires_grad=True)
self.layer_scale_2 = nn.Parameter(
layer_scale_init_value * torch.ones((dim)), requires_grad=True)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
elif isinstance(m, nn.Conv2d):
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
fan_out //= m.groups
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
if m.bias is not None:
m.bias.data.zero_()
def forward(self, x):
x = x + self.drop_path(self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) * self.attn(self.norm1(x)))
x = x + self.drop_path(self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) * self.mlp(self.norm2(x)))
return x
class OverlapPatchEmbed(nn.Module):
""" Image to Patch Embedding
"""
def __init__(self, img_size=224, patch_size=7, stride=4, in_chans=3, embed_dim=768):
super().__init__()
patch_size = to_2tuple(patch_size)
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=stride,
padding=(patch_size[0] // 2, patch_size[1] // 2))
self.norm = nn.BatchNorm2d(embed_dim)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
elif isinstance(m, nn.Conv2d):
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
fan_out //= m.groups
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
if m.bias is not None:
m.bias.data.zero_()
def forward(self, x):
x = self.proj(x)
_, _, H, W = x.shape
x = self.norm(x)
return x, H, W
class VAN(nn.Module):
def __init__(self, img_size=224, in_chans=3, num_classes=1000, embed_dims=[64, 128, 256, 512],
mlp_ratios=[4, 4, 4, 4], drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,
depths=[3, 4, 6, 3], num_stages=4, flag=False, k_size=7, pretrained_cfg=None):
super().__init__()
if flag == False:
self.num_classes = num_classes
self.depths = depths
self.num_stages = num_stages
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
cur = 0
for i in range(num_stages):
patch_embed = OverlapPatchEmbed(img_size=img_size if i == 0 else img_size // (2 ** (i + 1)),
patch_size=7 if i == 0 else 3,
stride=4 if i == 0 else 2,
in_chans=in_chans if i == 0 else embed_dims[i - 1],
embed_dim=embed_dims[i])
block = nn.ModuleList([Block(
dim=embed_dims[i], k_size=k_size, mlp_ratio=mlp_ratios[i], drop=drop_rate, drop_path=dpr[cur + j])
for j in range(depths[i])])
norm = norm_layer(embed_dims[i])
cur += depths[i]
setattr(self, f"patch_embed{i + 1}", patch_embed)
setattr(self, f"block{i + 1}", block)
setattr(self, f"norm{i + 1}", norm)
# classification head
self.head = nn.Linear(embed_dims[3], num_classes) if num_classes > 0 else nn.Identity()
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
elif isinstance(m, nn.Conv2d):
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
fan_out //= m.groups
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
if m.bias is not None:
m.bias.data.zero_()
def freeze_patch_emb(self):
self.patch_embed1.requires_grad = False
@torch.jit.ignore
def no_weight_decay(self):
return {'pos_embed1', 'pos_embed2', 'pos_embed3', 'pos_embed4', 'cls_token'} # has pos_embed may be better
def get_classifier(self):
return self.head
def reset_classifier(self, num_classes, global_pool=''):
self.num_classes = num_classes
self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
def forward_features(self, x):
B = x.shape[0]
for i in range(self.num_stages):
patch_embed = getattr(self, f"patch_embed{i + 1}")
block = getattr(self, f"block{i + 1}")
norm = getattr(self, f"norm{i + 1}")
x, H, W = patch_embed(x)
for blk in block:
x = blk(x)
x = x.flatten(2).transpose(1, 2)
x = norm(x)
if i == self.num_stages - 1:
x_feature_map = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
if i != self.num_stages - 1:
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
return x_feature_map, x.mean(dim=1)
def forward(self, x):
_, x = self.forward_features(x)
x = self.head(x)
return x
class DWConv(nn.Module):
def __init__(self, dim=768):
super(DWConv, self).__init__()
self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
def forward(self, x):
x = self.dwconv(x)
return x
def _conv_filter(state_dict, patch_size=16):
""" convert patch embedding weight from manual patchify + linear proj to conv"""
out_dict = {}
for k, v in state_dict.items():
if 'patch_embed.proj.weight' in k:
v = v.reshape((v.shape[0], 3, patch_size, patch_size))
out_dict[k] = v
return out_dict
model_urls = {
"van_tiny": "https://huggingface.co/Visual-Attention-Network/VAN-Tiny-original/resolve/main/van_tiny_754.pth.tar",
"van_small": "https://huggingface.co/Visual-Attention-Network/VAN-Small-original/resolve/main/van_small_811.pth.tar",
"van_base": "https://huggingface.co/Visual-Attention-Network/VAN-Base-original/resolve/main/van_base_828.pth.tar",
"van_large": "https://huggingface.co/Visual-Attention-Network/VAN-Large-original/resolve/main/van_large_839.pth.tar",
}
def load_model_weights(model, arch, kwargs):
url = model_urls[arch]
checkpoint = torch.hub.load_state_dict_from_url(
url=url, map_location="cpu", check_hash=True
)
strict = True
if "num_classes" in kwargs and kwargs["num_classes"] != 1000:
strict = False
del checkpoint["state_dict"]["head.weight"]
del checkpoint["state_dict"]["head.bias"]
print('load model weights....')
model.load_state_dict(checkpoint["state_dict"], strict=strict)
return model
@register_model
def van_tiny(pretrained=False, **kwargs):
model = VAN(
embed_dims=[32, 64, 160, 256], mlp_ratios=[8, 8, 4, 4],
norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 3, 5, 2],
**kwargs)
model.default_cfg = _cfg()
if pretrained:
model = load_model_weights(model, "van_tiny", kwargs)
return model
@register_model
def van_small(pretrained=False, **kwargs):
model = VAN(
embed_dims=[64, 128, 320, 512], mlp_ratios=[8, 8, 4, 4],
norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 4, 2],
**kwargs)
model.default_cfg = _cfg()
if pretrained:
model = load_model_weights(model, "van_small", kwargs)
return model
@register_model
def van_base(pretrained=False, **kwargs):
model = VAN(
embed_dims=[64, 128, 320, 512], mlp_ratios=[8, 8, 4, 4],
norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 3, 12, 3],
**kwargs)
model.default_cfg = _cfg()
if pretrained:
model = load_model_weights(model, "van_base", kwargs)
return model
2、添加YAML文件yolov8_SPPF_LSKA.yaml
添加到v8配置文件中ultralytics/cfg/models/v8/yolov8_SPPF_LSKA.yaml
# 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: 7 # 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, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF_LSKA, [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, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
3、添加SPPF_LSKA代码
(1)SPPF_LSKA代码添加到ultralytics/nn/modules/block.py
class SPPF_LSKA(nn.Module):
"""Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher."""
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
self.lska = LSKA(c_ * 4, k_size=11)
def forward(self, x):
"""Forward pass through Ghost Convolution block."""
x = self.cv1(x)
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(self.lska(torch.cat((x, y1, y2, self.m(y2)), 1)))
(2)block.py代码顶部__all__中添加’SPPF_LSKA’，并导入LSKA模块，添加时一定注意使用英文标点符号。
'SPPF_LSKA'
from .LSKA import LSKA
4、ultralytics/nn/modules/init.py注册模块
(1).block中导入SPPF_LSKA
(2)__all__中添加 ‘SPPF_LSKA’
5、ultralytics/nn/tasks.py注册模块
(2)在from ultralytics.nn.modules import导入SPPF_LSKA
(2)tasks.py中的def parse_model的if m in 语句中添加SPPF_LSKA
6、导入yaml文件训练
成功！！！！！！！
参考文章
https://blog.csdn.net/2301_78698967/article/details/139765522
https://blog.csdn.net/pope888/article/details/135536385