YOLOv5(6.1)结合ASFF(自适应空间融合）_yolov5结合域自适应

最近在给自己的网络添加ASFF，碰到蛮多问题，

• 一处是common.py文件中加入ASFFV5时，forward函数定义问题
  一开始复制的代码x未被定义，会报错，如下：
  
  重新定义即可：
  

• 一处是复制的ASFF_Detect类缺少一部分，后面找到了补齐的代码，下面已给出。

以下是YOLOv5(6.1)结合ASFF(自适应空间融合）的全流程：

1. common.py文件中加入ASFFV5

# ASFF
class ASFFV5(nn.Module):
    def __init__(self, level, multiplier=1, rfb=False, vis=False, act_cfg=True):
        """
        ASFF version for YoloV5 .
        different than YoloV3
        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 need change code manually.
        """
        super(ASFFV5, self).__init__()
        self.level = level
        self.dim = [int(1024 * multiplier), int(512 * multiplier),
                    int(256 * multiplier)]
        # print(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)

            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):  # l,m,s
        """
        # 128, 256, 512
        512, 256, 128
        from small -> large
        """
        x_level_0 = x[2]  # l
        x_level_1 = x[1]  # m
        x_level_2 = x[0]  # s
        # print('x_level_0: ', x_level_0.shape)
        # print('x_level_1: ', x_level_1.shape)
        # print('x_level_2: ', x_level_2.shape)
        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)
        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
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110

2. yolo.py文件中加入加入ASFF_Detect

class ASFF_Detect(nn.Module):  # add ASFFV5 layer and Rfb
    stride = None  # strides computed during build
    onnx_dynamic = False  # ONNX export parameter
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), multiplier=0.5, rfb=False, 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.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)
        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.inplace = inplace  # use in-place ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output
        result = []

        result.append(self.l2_fusion(x))
        result.append(self.l1_fusion(x))
        result.append(self.l0_fusion(x))
        x = result
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            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 + 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, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)

    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
        if torch_1_10:  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
            yv, xv = torch.meshgrid(y, x, indexing='ij')
        else:
            yv, xv = torch.meshgrid(y, x)
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        # print(anchor_grid)
        return grid, anchor_grid
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63

3. 在yolo.py文件Model类中做如下修改
yolo.py文件ctrl+F快捷键搜索isinstance(m, Detect)，在其后面添加 or isinstance(m, ASFF_Detect)，共有三处：

4. 在yolo.py文件parse_model函数下做如下修改
和Detect一样的代码。

        elif m is 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 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)
1
2
3
4
5
6
7
8

5. 修改yaml文件，只需将Detect替换为ASFF_Detect

# YOLOv5 
声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/木道寻08/article/detail/869342