File size: 6,378 Bytes
c295391
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# This file is modified version from the original convnext
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.


from functools import partial

import torch
import torch.nn as nn
import torch.nn.functional as F

class Block(nn.Module):
    r""" ConvNeXt Block. There are two equivalent implementations:

    (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)

    (2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back

    We use (2) as we find it slightly faster in PyTorch

    

    Args:

        dim (int): Number of input channels.

        drop_path (float): Stochastic depth rate. Default: 0.0

        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.

    """
    def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
        self.norm = LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 4 * dim) # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)), 
                                    requires_grad=True) if layer_scale_init_value > 0 else None
        self.drop_path = nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)

        x = input + self.drop_path(x)
        return x

# @BACKBONES.register_module()
class ConvNeXt(nn.Module):
    r""" ConvNeXt

        A PyTorch impl of : `A ConvNet for the 2020s`  -

          https://arxiv.org/pdf/2201.03545.pdf



    Args:

        in_chans (int): Number of input image channels. Default: 3

        num_classes (int): Number of classes for classification head. Default: 1000

        depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]

        dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]

        drop_path_rate (float): Stochastic depth rate. Default: 0.

        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.

        head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.

    """
    def __init__(self, in_chans=3, depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], 

                 drop_path_rate=0., layer_scale_init_value=1e-6, out_indices=[0, 1, 2, 3], use_checkpoint=False

                 ):
        super().__init__()
        self.use_checkpoint = use_checkpoint
        self.downsample_layers = nn.ModuleList() # stem and 3 intermediate downsampling conv layers
        stem = nn.Sequential(
            nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
            LayerNorm(dims[0], eps=1e-6, data_format="channels_first")
        )
        self.downsample_layers.append(stem)
        for i in range(3):
            downsample_layer = nn.Sequential(
                    LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
                    nn.Conv2d(dims[i], dims[i+1], kernel_size=2, stride=2),
            )
            self.downsample_layers.append(downsample_layer)

        self.stages = nn.ModuleList() # 4 feature resolution stages, each consisting of multiple residual blocks
        dp_rates=[x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] 
        cur = 0
        for i in range(4):
            stage = nn.Sequential(
                *[Block(dim=dims[i], drop_path=dp_rates[cur + j], 
                layer_scale_init_value=layer_scale_init_value) for j in range(depths[i])]
            )


            self.stages.append(stage)
            cur += depths[i]

        self.out_indices = out_indices

        norm_layer = partial(LayerNorm, eps=1e-6, data_format="channels_first")
        for i_layer in range(4):
            layer = norm_layer(dims[i_layer])
            layer_name = f'norm{i_layer}'
            self.add_module(layer_name, layer)


    
    def forward_features(self, x):
        outs = []
        for i in range(4):
            x = self.downsample_layers[i](x)
            x = self.stages[i](x)            
            
            if i in self.out_indices:
                norm_layer = getattr(self, f'norm{i}')
                x_out = norm_layer(x)
                outs.append(x_out)

        return tuple(outs)

    def forward(self, x):
        x = self.forward_features(x)
        return x

class LayerNorm(nn.Module):
    r""" LayerNorm that supports two data formats: channels_last (default) or channels_first. 

    The ordering of the dimensions in the inputs. channels_last corresponds to inputs with 

    shape (batch_size, height, width, channels) while channels_first corresponds to inputs 

    with shape (batch_size, channels, height, width).

    """
    def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ["channels_last", "channels_first"]:
            raise NotImplementedError 
        self.normalized_shape = (normalized_shape, )
    
    def forward(self, x):
        if self.data_format == "channels_last":
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == "channels_first":
            u = x.mean(1, keepdim=True)
            s = (x - u).pow(2).mean(1, keepdim=True)
            x = (x - u) / torch.sqrt(s + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x