File size: 13,440 Bytes
49f3b67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Convolution modules
"""

import math

import numpy as np
import torch
import torch.nn as nn

__all__ = ('Conv', 'LightConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus', 'GhostConv',
           'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'RepConv')


def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p

# Pavlo's implementation with switch to deploy
class Conv(nn.Module):
    default_act = nn.SiLU()  # default activation

    def __init__(self, a, b, kernel_size=1, stride=1, padding=None, g=1, dilation=1, bn_weight_init=1, bias=False, act=True):
        super().__init__()

        self.conv = torch.nn.Conv2d(a, b, kernel_size, stride, autopad(kernel_size, padding, dilation), dilation, g, bias=False)
        if 1:
            self.bn = torch.nn.BatchNorm2d(b)
            torch.nn.init.constant_(self.bn.weight, bn_weight_init)
            torch.nn.init.constant_(self.bn.bias, 0)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()


    def forward(self,x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.act(x)
        return x

    @torch.no_grad()
    def switch_to_deploy(self):
        if not isinstance(self.bn, nn.Identity):
            # return 1
            c, bn = self.conv, self.bn
            w = bn.weight / (bn.running_var + bn.eps) ** 0.5
            w = c.weight * w[:, None, None, None]
            b = bn.bias - bn.running_mean * bn.weight / \
                (bn.running_var + bn.eps)**0.5
            # m = torch.nn.Conv2d(w.size(1) * c.groups,
            #                     w.size(0),
            #                     w.shape[2:],
            #                     stride=c.stride,
            #                     padding=c.padding,
            #                     dilation=c.dilation,
            #                     groups=c.groups)
            self.conv.weight.data.copy_(w)
            self.conv.bias = nn.Parameter(b)
            # self.conv.bias.data.copy_(b)
            # self.conv = m.to(c.weight.device)
            self.bn = nn.Identity()

# class Conv(nn.Module):
#     """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
#     default_act = nn.SiLU()  # default activation

#     def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
#         """Initialize Conv layer with given arguments including activation."""
#         super().__init__()
#         self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
#         self.bn = nn.BatchNorm2d(c2)
#         self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

#     def forward(self, x):
#         """Apply convolution, batch normalization and activation to input tensor."""
#         return self.act(self.bn(self.conv(x)))

#     def forward_fuse(self, x):
#         """Perform transposed convolution of 2D data."""
#         return self.act(self.conv(x))


class Conv2(Conv):
    """Simplified RepConv module with Conv fusing."""

    def __init__(self, c1, c2, k=3, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__(c1, c2, k, s, p, g=g, d=d, act=act)
        self.cv2 = nn.Conv2d(c1, c2, 1, s, autopad(1, p, d), groups=g, dilation=d, bias=False)  # add 1x1 conv

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x) + self.cv2(x)))

    def fuse_convs(self):
        """Fuse parallel convolutions."""
        w = torch.zeros_like(self.conv.weight.data)
        i = [x // 2 for x in w.shape[2:]]
        w[:, :, i[0]:i[0] + 1, i[1]:i[1] + 1] = self.cv2.weight.data.clone()
        self.conv.weight.data += w
        self.__delattr__('cv2')


class LightConv(nn.Module):
    """Light convolution with args(ch_in, ch_out, kernel).
    https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
    """

    def __init__(self, c1, c2, k=1, act=nn.ReLU()):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv1 = Conv(c1, c2, 1, act=False)
        self.conv2 = DWConv(c2, c2, k, act=act)

    def forward(self, x):
        """Apply 2 convolutions to input tensor."""
        return self.conv2(self.conv1(x))


class DWConv(Conv):
    """Depth-wise convolution."""

    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)


class DWConvTranspose2d(nn.ConvTranspose2d):
    """Depth-wise transpose convolution."""

    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))


class ConvTranspose(nn.Module):
    """Convolution transpose 2d layer."""
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
        """Initialize ConvTranspose2d layer with batch normalization and activation function."""
        super().__init__()
        self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn)
        self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity()
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        """Applies transposed convolutions, batch normalization and activation to input."""
        return self.act(self.bn(self.conv_transpose(x)))

    def forward_fuse(self, x):
        """Applies activation and convolution transpose operation to input."""
        return self.act(self.conv_transpose(x))


class Focus(nn.Module):
    """Focus wh information into c-space."""

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
        # self.contract = Contract(gain=2)

    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
        return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
        # return self.conv(self.contract(x))


class GhostConv(nn.Module):
    """Ghost Convolution https://github.com/huawei-noah/ghostnet."""

    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
        super().__init__()
        c_ = c2 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)

    def forward(self, x):
        """Forward propagation through a Ghost Bottleneck layer with skip connection."""
        y = self.cv1(x)
        return torch.cat((y, self.cv2(y)), 1)


class RepConv(nn.Module):
    """RepConv is a basic rep-style block, including training and deploy status
    This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    """
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

        self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

    def forward_fuse(self, x):
        """Forward process"""
        return self.act(self.conv(x))

    def forward(self, x):
        """Forward process"""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)

    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _avg_to_3x3_tensor(self, avgp):
        channels = self.c1
        groups = self.g
        kernel_size = avgp.kernel_size
        input_dim = channels // groups
        k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
        k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
        return k

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        if branch is None:
            return 0, 0
        if isinstance(branch, Conv):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def fuse_convs(self):
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')


class ChannelAttention(nn.Module):
    """Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet."""

    def __init__(self, channels: int) -> None:
        super().__init__()
        self.pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
        self.act = nn.Sigmoid()

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return x * self.act(self.fc(self.pool(x)))


class SpatialAttention(nn.Module):
    """Spatial-attention module."""

    def __init__(self, kernel_size=7):
        """Initialize Spatial-attention module with kernel size argument."""
        super().__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.act = nn.Sigmoid()

    def forward(self, x):
        """Apply channel and spatial attention on input for feature recalibration."""
        return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))


class CBAM(nn.Module):
    """Convolutional Block Attention Module."""

    def __init__(self, c1, kernel_size=7):  # ch_in, kernels
        super().__init__()
        self.channel_attention = ChannelAttention(c1)
        self.spatial_attention = SpatialAttention(kernel_size)

    def forward(self, x):
        """Applies the forward pass through C1 module."""
        return self.spatial_attention(self.channel_attention(x))


class Concat(nn.Module):
    """Concatenate a list of tensors along dimension."""

    def __init__(self, dimension=1):
        """Concatenates a list of tensors along a specified dimension."""
        super().__init__()
        self.d = dimension

    def forward(self, x):
        """Forward pass for the YOLOv8 mask Proto module."""
        return torch.cat(x, self.d)