YOLOv5 6.0/6.1结合ASFF
前言
YOLO小白纯干货分享！！！
一、主要修改代码
二、使用步骤
1. models/common.py：加入要修改的代码, 类ASFFV5 class ASFFV5(nn.Module):
class ASFFV5(nn.Module):
def __init__(self, level, multiplier=1, rfb=False, vis=False, act_cfg=True):
"""
ASFF version for YoloV5 only.
Since YoloV5 outputs 3 layer of feature maps with different channels
which is different than YoloV3
normally, multiplier should be 1, 0.5
which means, the channel of ASFF can be
512, 256, 128 -> multiplier=1
256, 128, 64 -> multiplier=0.5
For even smaller, you gonna need change code manually.
"""
super(ASFFV5, self).__init__()
self.level = level
self.dim = [int(1024*multiplier), int(512*multiplier),
int(256*multiplier)]
#print("dim:",self.dim)
self.inter_dim = self.dim[self.level]
if level == 0:
self.stride_level_1 = Conv(int(512*multiplier), self.inter_dim, 3, 2)
#print(self.dim)
self.stride_level_2 = Conv(int(256*multiplier), self.inter_dim, 3, 2)
self.expand = Conv(self.inter_dim, int(
1024*multiplier), 3, 1)
elif level == 1:
self.compress_level_0 = Conv(
int(1024*multiplier), self.inter_dim, 1, 1)
self.stride_level_2 = Conv(
int(256*multiplier), self.inter_dim, 3, 2)
self.expand = Conv(self.inter_dim, int(512*multiplier), 3, 1)
elif level == 2:
self.compress_level_0 = Conv(
int(1024*multiplier), self.inter_dim, 1, 1)
self.compress_level_1 = Conv(
int(512*multiplier), self.inter_dim, 1, 1)
self.expand = Conv(self.inter_dim, int(
256*multiplier), 3, 1)
# when adding rfb, we use half number of channels to save memory
compress_c = 8 if rfb else 16
self.weight_level_0 = Conv(
self.inter_dim, compress_c, 1, 1)
self.weight_level_1 = Conv(
self.inter_dim, compress_c, 1, 1)
self.weight_level_2 = Conv(
self.inter_dim, compress_c, 1, 1)
self.weight_levels = Conv(
compress_c*3, 3, 1, 1)
self.vis = vis
def forward(self, x_level_0, x_level_1, x_level_2): #s,m,l
"""
# 128, 256, 512
512, 256, 128
from small -> large
"""
# print('x_level_0: ', x_level_0.shape)
# print('x_level_1: ', x_level_1.shape)
# print('x_level_2: ', x_level_2.shape)
x_level_0=x[2]
x_level_1=x[1]
x_level_2=x[0]
if self.level == 0:
level_0_resized = x_level_0
level_1_resized = self.stride_level_1(x_level_1)
level_2_downsampled_inter = F.max_pool2d(
x_level_2, 3, stride=2, padding=1)
level_2_resized = self.stride_level_2(level_2_downsampled_inter)
#print('X——level_0: ', level_2_downsampled_inter.shape)
elif self.level == 1:
level_0_compressed = self.compress_level_0(x_level_0)
level_0_resized = F.interpolate(
level_0_compressed, scale_factor=2, mode='nearest')
level_1_resized = x_level_1
level_2_resized = self.stride_level_2(x_level_2)
elif self.level == 2:
level_0_compressed = self.compress_level_0(x_level_0)
level_0_resized = F.interpolate(
level_0_compressed, scale_factor=4, mode='nearest')
x_level_1_compressed = self.compress_level_1(x_level_1)
level_1_resized = F.interpolate(
x_level_1_compressed, scale_factor=2, mode='nearest')
level_2_resized = x_level_2
# print('level: {}, l1_resized: {}, l2_resized: {}'.format(self.level,
# level_1_resized.shape, level_2_resized.shape))
level_0_weight_v = self.weight_level_0(level_0_resized)
level_1_weight_v = self.weight_level_1(level_1_resized)
level_2_weight_v = self.weight_level_2(level_2_resized)
# print('level_0_weight_v: ', level_0_weight_v.shape)
# print('level_1_weight_v: ', level_1_weight_v.shape)
# print('level_2_weight_v: ', level_2_weight_v.shape)
levels_weight_v = torch.cat(
(level_0_weight_v, level_1_weight_v, level_2_weight_v), 1)
levels_weight = self.weight_levels(levels_weight_v)
levels_weight = F.softmax(levels_weight, dim=1)
fused_out_reduced = level_0_resized * levels_weight[:, 0:1, :, :] +\
level_1_resized * levels_weight[:, 1:2, :, :] +\
level_2_resized * levels_weight[:, 2:, :, :]
out = self.expand(fused_out_reduced)
if self.vis:
return out, levels_weight, fused_out_reduced.sum(dim=1)
else:
return out
2. models/yolo.py：添加 类ASFF_Detect
然后在yolo.py 中 Detect 类下面，添加一个ASFF_Detect类
class ASFF_Detect(nn.Module): #add ASFFV5 layer and Rfb
stride = None # strides computed during build
export = False # onnx export
def __init__(self, nc=80, anchors=(), multiplier=0.5,rfb=False,ch=()): # detection layer
super(ASFF_Detect, self).__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.l0_fusion = ASFFV5(level=0, multiplier=multiplier,rfb=rfb)
self.l1_fusion = ASFFV5(level=1, multiplier=multiplier,rfb=rfb)
self.l2_fusion = ASFFV5(level=2, multiplier=multiplier,rfb=rfb)
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
self.register_buffer('anchors', a) # shape(nl,na,2)
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
接着在 yolo.py的parse_model 中把函数放到模型的代码里：
（大概在283行左右）
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,CBAM,ResBlock_CBAM,
C3]:
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3]:
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum([ch[x] for x in f])
elif m is ASFF_Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
elif m is ASFFV5:
c2=args[1]
else:
c2 = ch[f]
3.models/yolov5s-asff.yaml
在models文件夹下新建对应的yolov5s-asff.yaml 文件
然后将yolov5s.yaml的内容复制过来，将 head 部分的最后一行进行修改；
将[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ]
修改成下面：
[[17, 20, 23], 1, ASFF_Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
4.查看网络结构
修改 models/yolo.py --cfg models/yolov5s-asff.yaml
接下来run yolo.py 即可查看网络结构
5.将train.py 中 --cfg中的 yaml 文件修改成本文文件即可，开始训练
总结
本人在多个数据集上做了大量实验，针对不同的数据集效果不同，需要大家进行实验。有效果有提升的情况占大多数。
最后，希望能互粉一下，做个朋友，一起学习交流。