File size: 5,658 Bytes
3e06e1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
# Copyright (c) OpenMMLab. All rights reserved.
import math

import torch
import torch.nn as nn
from mmcv.cnn import ConvModule, DepthwiseSeparableConvModule
from mmengine.model import BaseModule

from mmdet.registry import MODELS
from ..layers import CSPLayer


@MODELS.register_module()
class YOLOXPAFPN(BaseModule):
    """Path Aggregation Network used in YOLOX.

    Args:
        in_channels (List[int]): Number of input channels per scale.
        out_channels (int): Number of output channels (used at each scale)
        num_csp_blocks (int): Number of bottlenecks in CSPLayer. Default: 3
        use_depthwise (bool): Whether to depthwise separable convolution in
            blocks. Default: False
        upsample_cfg (dict): Config dict for interpolate layer.
            Default: `dict(scale_factor=2, mode='nearest')`
        conv_cfg (dict, optional): Config dict for convolution layer.
            Default: None, which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN')
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='Swish')
        init_cfg (dict or list[dict], optional): Initialization config dict.
            Default: None.
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 num_csp_blocks=3,
                 use_depthwise=False,
                 upsample_cfg=dict(scale_factor=2, mode='nearest'),
                 conv_cfg=None,
                 norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
                 act_cfg=dict(type='Swish'),
                 init_cfg=dict(
                     type='Kaiming',
                     layer='Conv2d',
                     a=math.sqrt(5),
                     distribution='uniform',
                     mode='fan_in',
                     nonlinearity='leaky_relu')):
        super(YOLOXPAFPN, self).__init__(init_cfg)
        self.in_channels = in_channels
        self.out_channels = out_channels

        conv = DepthwiseSeparableConvModule if use_depthwise else ConvModule

        # build top-down blocks
        self.upsample = nn.Upsample(**upsample_cfg)
        self.reduce_layers = nn.ModuleList()
        self.top_down_blocks = nn.ModuleList()
        for idx in range(len(in_channels) - 1, 0, -1):
            self.reduce_layers.append(
                ConvModule(
                    in_channels[idx],
                    in_channels[idx - 1],
                    1,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))
            self.top_down_blocks.append(
                CSPLayer(
                    in_channels[idx - 1] * 2,
                    in_channels[idx - 1],
                    num_blocks=num_csp_blocks,
                    add_identity=False,
                    use_depthwise=use_depthwise,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))

        # build bottom-up blocks
        self.downsamples = nn.ModuleList()
        self.bottom_up_blocks = nn.ModuleList()
        for idx in range(len(in_channels) - 1):
            self.downsamples.append(
                conv(
                    in_channels[idx],
                    in_channels[idx],
                    3,
                    stride=2,
                    padding=1,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))
            self.bottom_up_blocks.append(
                CSPLayer(
                    in_channels[idx] * 2,
                    in_channels[idx + 1],
                    num_blocks=num_csp_blocks,
                    add_identity=False,
                    use_depthwise=use_depthwise,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))

        self.out_convs = nn.ModuleList()
        for i in range(len(in_channels)):
            self.out_convs.append(
                ConvModule(
                    in_channels[i],
                    out_channels,
                    1,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))

    def forward(self, inputs):
        """
        Args:
            inputs (tuple[Tensor]): input features.

        Returns:
            tuple[Tensor]: YOLOXPAFPN features.
        """
        assert len(inputs) == len(self.in_channels)

        # top-down path
        inner_outs = [inputs[-1]]
        for idx in range(len(self.in_channels) - 1, 0, -1):
            feat_heigh = inner_outs[0]
            feat_low = inputs[idx - 1]
            feat_heigh = self.reduce_layers[len(self.in_channels) - 1 - idx](
                feat_heigh)
            inner_outs[0] = feat_heigh

            upsample_feat = self.upsample(feat_heigh)

            inner_out = self.top_down_blocks[len(self.in_channels) - 1 - idx](
                torch.cat([upsample_feat, feat_low], 1))
            inner_outs.insert(0, inner_out)

        # bottom-up path
        outs = [inner_outs[0]]
        for idx in range(len(self.in_channels) - 1):
            feat_low = outs[-1]
            feat_height = inner_outs[idx + 1]
            downsample_feat = self.downsamples[idx](feat_low)
            out = self.bottom_up_blocks[idx](
                torch.cat([downsample_feat, feat_height], 1))
            outs.append(out)

        # out convs
        for idx, conv in enumerate(self.out_convs):
            outs[idx] = conv(outs[idx])

        return tuple(outs)