目录
Yolov5/Yolov7加入Yolov8 c2f模块,小目标涨点
各种技巧实战测试
decouple head
原文:
涨点技巧:Detect系列---Yolov5/Yolov7加入解耦头Decoupled_Detect,涨点明显_AI小怪兽的博客-CSDN博客
yolov5中head修改为decouple head详解_python_
class Detect(nn.Module):
stride = None # strides computed during build
onnx_dynamic = False # ONNX export parameter
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
super().__init__()
self.nc = nc # number of classes
self.no = nc + 5 # number of outputs per anchor
self.nl = len(anchors) # number of detection layers
self.na = len(anchors[0]) // 2 # number of anchors
self.grid = [torch.zeros(1)] * self.nl # init grid
self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
# self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
self.m_box = nn.ModuleList(nn.Conv2d(256, 4 * self.na, 1) for x in ch) # output conv
self.m_conf = nn.ModuleList(nn.Conv2d(256, 1 * self.na, 1) for x in ch) # output conv
self.m_labels = nn.ModuleList(nn.Conv2d(256, self.nc * self.na, 1) for x in ch) # output conv
self.base_conv = nn.ModuleList(BaseConv(in_channels = x, out_channels = 256, ksize = 1, stride = 1) for x in ch)
self.cls_convs = nn.ModuleList(BaseConv(in_channels = 256, out_channels = 256, ksize = 3, stride = 1) for x in ch)
self.reg_convs = nn.ModuleList(BaseConv(in_channels = 256, out_channels = 256, ksize = 3, stride = 1) for x in ch)
# self.m = nn.ModuleList(nn.Conv2d(x, 4 * self.na, 1) for x in ch, nn.Conv2d(x, 1 * self.na, 1) for x in ch,nn.Conv2d(x, self.nc * self.na, 1) for x in ch)
self.inplace = inplace # use in-place ops (e.g. slice assignment)self.ch = ch
def forward(self, x):
z = [] # inference output
for i in range(self.nl):
# # x[i] = self.m[i](x[i]) # convs
# print("&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&", i)
# print(x[i].shape)
# print(self.base_conv[i])
# print("%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
x_feature = self.base_conv[i](x[i])
# x_feature = x[i]
cls_feature = self.cls_convs[i](x_feature)
reg_feature = self.reg_convs[i](x_feature)
# reg_feature = x_feature
m_box = self.m_box[i](reg_feature)
m_conf = self.m_conf[i](reg_feature)
m_labels = self.m_labels[i](cls_feature)
x[i] = torch.cat((m_box,m_conf, m_labels),1)
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
if not self.training: # inference
if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
y = x[i].sigmoid()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
y = torch.cat((xy, wh, y[..., 4:]), -1)
z.append(y.view(bs, -1, self.no))
return x if self.training else (torch.cat(z, 1), x)
yolo中添加:
def get_activation(name="silu", inplace=True):
if name == "silu":
module = nn.SiLU(inplace=inplace)
elif name == "relu":
module = nn.ReLU(inplace=inplace)
elif name == "lrelu":
module = nn.LeakyReLU(0.1, inplace=inplace)
else:
raise AttributeError("Unsupported act type: {}".format(name))
return module
class BaseConv(nn.Module):
"""A Conv2d -> Batchnorm -> silu/leaky relu block"""
def __init__(
self, in_channels, out_channels, ksize, stride, groups=1, bias=False, act="silu"
):
super().__init__()
# same padding
pad = (ksize - 1) // 2
self.conv = nn.Conv2d(
in_channels,
out_channels,
kernel_size=ksize,
stride=stride,
padding=pad,
groups=groups,
bias=bias,
)
self.bn = nn.BatchNorm2d(out_channels)
self.act = get_activation(act, inplace=True)
def forward(self, x):
# print(self.bn(self.conv(x)).shape)
return self.act(self.bn(self.conv(x)))
# return self.bn(self.conv(x))
def fuseforward(self, x):
return self.act(self.conv(x))
Yolov5/Yolov7加入Yolov8 c2f模块,小目标涨点
class v8_C2fBottleneck(nn.Module):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5): # ch_in, ch_out, shortcut, groups, kernels, expand
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, k[0], 1)
self.cv2 = Conv(c_, c2, k[1], 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C2f(nn.Module):
# CSP Bottleneck with 2 convolutions
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
self.c = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
self.m = nn.ModuleList(v8_C2fBottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
def forward(self, x):
y = list(self.cv1(x).split((self.c, self.c), 1))
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))
————————————————
版权声明:本文为CSDN博主「AI小怪兽」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/m0_63774211/article/details/129493630
2)在yolo.py
中添加C2f(PS:快速搜索C3对应位置)
1)加入backbone
# YOLOv5 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, 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, [1024]]
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
2) 加入head
# YOLOv5 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C2f, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C2f, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]