File size: 7,138 Bytes
71c9afb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import math
import torch
from torch import nn as nn
from torch.nn import functional as F
from torch.nn import init as init
from torch.nn.modules.batchnorm import _BatchNorm

@torch.no_grad()
def default_init_weights(module_list, scale=1, bias_fill=0, **kwargs):
    """Initialize network weights.

    Args:
        module_list (list[nn.Module] | nn.Module): Modules to be initialized.
        scale (float): Scale initialized weights, especially for residual
            blocks. Default: 1.
        bias_fill (float): The value to fill bias. Default: 0
        kwargs (dict): Other arguments for initialization function.
    """
    if not isinstance(module_list, list):
        module_list = [module_list]
    for module in module_list:
        for m in module.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, **kwargs)
                m.weight.data *= scale
                if m.bias is not None:
                    m.bias.data.fill_(bias_fill)
            elif isinstance(m, nn.Linear):
                init.kaiming_normal_(m.weight, **kwargs)
                m.weight.data *= scale
                if m.bias is not None:
                    m.bias.data.fill_(bias_fill)
            elif isinstance(m, _BatchNorm):
                init.constant_(m.weight, 1)
                if m.bias is not None:
                    m.bias.data.fill_(bias_fill)


def make_layer(basic_block, num_basic_block, **kwarg):
    """Make layers by stacking the same blocks.

    Args:
        basic_block (nn.module): nn.module class for basic block.
        num_basic_block (int): number of blocks.

    Returns:
        nn.Sequential: Stacked blocks in nn.Sequential.
    """
    layers = []
    for _ in range(num_basic_block):
        layers.append(basic_block(**kwarg))
    return nn.Sequential(*layers)


class ResidualBlockNoBN(nn.Module):
    """Residual block without BN.

    It has a style of:
        ---Conv-ReLU-Conv-+-
         |________________|

    Args:
        num_feat (int): Channel number of intermediate features.
            Default: 64.
        res_scale (float): Residual scale. Default: 1.
        pytorch_init (bool): If set to True, use pytorch default init,
            otherwise, use default_init_weights. Default: False.
    """

    def __init__(self, num_feat=64, res_scale=1, pytorch_init=False):
        super(ResidualBlockNoBN, self).__init__()
        self.res_scale = res_scale
        self.conv1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
        self.conv2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1, bias=True)
        self.relu = nn.ReLU(inplace=True)

        if not pytorch_init:
            default_init_weights([self.conv1, self.conv2], 0.1)

    def forward(self, x):
        identity = x
        out = self.conv2(self.relu(self.conv1(x)))
        return identity + out * self.res_scale


class Upsample(nn.Sequential):
    """Upsample module.

    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.
    """

    def __init__(self, scale, num_feat):
        m = []
        if (scale & (scale - 1)) == 0:  # scale = 2^n
            for _ in range(int(math.log(scale, 2))):
                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
                m.append(nn.PixelShuffle(2))
        elif scale == 3:
            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
            m.append(nn.PixelShuffle(3))
        else:
            raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
        super(Upsample, self).__init__(*m)


def flow_warp(x, flow, interp_mode='bilinear', padding_mode='zeros', align_corners=True):
    """Warp an image or feature map with optical flow.

    Args:
        x (Tensor): Tensor with size (n, c, h, w).
        flow (Tensor): Tensor with size (n, h, w, 2), normal value.
        interp_mode (str): 'nearest' or 'bilinear'. Default: 'bilinear'.
        padding_mode (str): 'zeros' or 'border' or 'reflection'.
            Default: 'zeros'.
        align_corners (bool): Before pytorch 1.3, the default value is
            align_corners=True. After pytorch 1.3, the default value is
            align_corners=False. Here, we use the True as default.

    Returns:
        Tensor: Warped image or feature map.
    """
    assert x.size()[-2:] == flow.size()[1:3]
    _, _, h, w = x.size()
    # create mesh grid
    grid_y, grid_x = torch.meshgrid(torch.arange(0, h).type_as(x), torch.arange(0, w).type_as(x))
    grid = torch.stack((grid_x, grid_y), 2).float()  # W(x), H(y), 2
    grid.requires_grad = False

    vgrid = grid + flow
    # scale grid to [-1,1]
    vgrid_x = 2.0 * vgrid[:, :, :, 0] / max(w - 1, 1) - 1.0
    vgrid_y = 2.0 * vgrid[:, :, :, 1] / max(h - 1, 1) - 1.0
    vgrid_scaled = torch.stack((vgrid_x, vgrid_y), dim=3)
    output = F.grid_sample(x, vgrid_scaled, mode=interp_mode, padding_mode=padding_mode, align_corners=align_corners)

    # TODO, what if align_corners=False
    return output


def resize_flow(flow, size_type, sizes, interp_mode='bilinear', align_corners=False):
    """Resize a flow according to ratio or shape.

    Args:
        flow (Tensor): Precomputed flow. shape [N, 2, H, W].
        size_type (str): 'ratio' or 'shape'.
        sizes (list[int | float]): the ratio for resizing or the final output
            shape.
            1) The order of ratio should be [ratio_h, ratio_w]. For
            downsampling, the ratio should be smaller than 1.0 (i.e., ratio
            < 1.0). For upsampling, the ratio should be larger than 1.0 (i.e.,
            ratio > 1.0).
            2) The order of output_size should be [out_h, out_w].
        interp_mode (str): The mode of interpolation for resizing.
            Default: 'bilinear'.
        align_corners (bool): Whether align corners. Default: False.

    Returns:
        Tensor: Resized flow.
    """
    _, _, flow_h, flow_w = flow.size()
    if size_type == 'ratio':
        output_h, output_w = int(flow_h * sizes[0]), int(flow_w * sizes[1])
    elif size_type == 'shape':
        output_h, output_w = sizes[0], sizes[1]
    else:
        raise ValueError(f'Size type should be ratio or shape, but got type {size_type}.')

    input_flow = flow.clone()
    ratio_h = output_h / flow_h
    ratio_w = output_w / flow_w
    input_flow[:, 0, :, :] *= ratio_w
    input_flow[:, 1, :, :] *= ratio_h
    resized_flow = F.interpolate(
        input=input_flow, size=(output_h, output_w), mode=interp_mode, align_corners=align_corners)
    return resized_flow


# TODO: may write a cpp file
def pixel_unshuffle(x, scale):
    """ Pixel unshuffle.

    Args:
        x (Tensor): Input feature with shape (b, c, hh, hw).
        scale (int): Downsample ratio.

    Returns:
        Tensor: the pixel unshuffled feature.
    """
    b, c, hh, hw = x.size()
    out_channel = c * (scale**2)
    assert hh % scale == 0 and hw % scale == 0
    h = hh // scale
    w = hw // scale
    x_view = x.view(b, c, h, scale, w, scale)
    return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)