models/e4e/encoders/helpers.py

from collections import namedtuple
import torch
import torch.nn.functional as F
from torch.nn import Conv2d, BatchNorm2d, PReLU, ReLU, Sigmoid, MaxPool2d, AdaptiveAvgPool2d, Sequential, Module

"""
ArcFace implementation from [TreB1eN](https://github.com/TreB1eN/InsightFace_Pytorch)
"""


class Flatten(Module):
    def forward(self, input):
        return input.view(input.size(0), -1)


def l2_norm(input, axis=1):
    norm = torch.norm(input, 2, axis, True)
    output = torch.div(input, norm)
    return output


class Bottleneck(namedtuple('Block', ['in_channel', 'depth', 'stride'])):
    """ A named tuple describing a ResNet block. """


def get_block(in_channel, depth, num_units, stride=2):
    return [Bottleneck(in_channel, depth, stride)] + [Bottleneck(depth, depth, 1) for i in range(num_units - 1)]


def get_blocks(num_layers):
    if num_layers == 50:
        blocks = [
            get_block(in_channel=64, depth=64, num_units=3),
            get_block(in_channel=64, depth=128, num_units=4),
            get_block(in_channel=128, depth=256, num_units=14),
            get_block(in_channel=256, depth=512, num_units=3)
        ]
    elif num_layers == 100:
        blocks = [
            get_block(in_channel=64, depth=64, num_units=3),
            get_block(in_channel=64, depth=128, num_units=13),
            get_block(in_channel=128, depth=256, num_units=30),
            get_block(in_channel=256, depth=512, num_units=3)
        ]
    elif num_layers == 152:
        blocks = [
            get_block(in_channel=64, depth=64, num_units=3),
            get_block(in_channel=64, depth=128, num_units=8),
            get_block(in_channel=128, depth=256, num_units=36),
            get_block(in_channel=256, depth=512, num_units=3)
        ]
    else:
        raise ValueError("Invalid number of layers: {}. Must be one of [50, 100, 152]".format(num_layers))
    return blocks


class SEModule(Module):
    def __init__(self, channels, reduction):
        super(SEModule, self).__init__()
        self.avg_pool = AdaptiveAvgPool2d(1)
        self.fc1 = Conv2d(channels, channels // reduction, kernel_size=1, padding=0, bias=False)
        self.relu = ReLU(inplace=True)
        self.fc2 = Conv2d(channels // reduction, channels, kernel_size=1, padding=0, bias=False)
        seltorch.sigmoid = Sigmoid()

    def forward(self, x):
        module_input = x
        x = self.avg_pool(x)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = seltorch.sigmoid(x)
        return module_input * x


class bottleneck_IR(Module):
    def __init__(self, in_channel, depth, stride):
        super(bottleneck_IR, self).__init__()
        if in_channel == depth:
            self.shortcut_layer = MaxPool2d(1, stride)
        else:
            self.shortcut_layer = Sequential(
                Conv2d(in_channel, depth, (1, 1), stride, bias=False),
                BatchNorm2d(depth)
            )
        self.res_layer = Sequential(
            BatchNorm2d(in_channel),
            Conv2d(in_channel, depth, (3, 3), (1, 1), 1, bias=False), PReLU(depth),
            Conv2d(depth, depth, (3, 3), stride, 1, bias=False), BatchNorm2d(depth)
        )

    def forward(self, x):
        shortcut = self.shortcut_layer(x)
        res = self.res_layer(x)
        return res + shortcut


class bottleneck_IR_SE(Module):
    def __init__(self, in_channel, depth, stride):
        super(bottleneck_IR_SE, self).__init__()
        if in_channel == depth:
            self.shortcut_layer = MaxPool2d(1, stride)
        else:
            self.shortcut_layer = Sequential(
                Conv2d(in_channel, depth, (1, 1), stride, bias=False),
                BatchNorm2d(depth)
            )
        self.res_layer = Sequential(
            BatchNorm2d(in_channel),
            Conv2d(in_channel, depth, (3, 3), (1, 1), 1, bias=False),
            PReLU(depth),
            Conv2d(depth, depth, (3, 3), stride, 1, bias=False),
            BatchNorm2d(depth),
            SEModule(depth, 16)
        )

    def forward(self, x):
        shortcut = self.shortcut_layer(x)
        res = self.res_layer(x)
        return res + shortcut


def _upsample_add(x, y):
    """Upsample and add two feature maps.
    Args:
      x: (Variable) top feature map to be upsampled.
      y: (Variable) lateral feature map.
    Returns:
      (Variable) added feature map.
    Note in PyTorch, when input size is odd, the upsampled feature map
    with `F.upsample(..., scale_factor=2, mode='nearest')`
    maybe not equal to the lateral feature map size.
    e.g.
    original input size: [N,_,15,15] ->
    conv2d feature map size: [N,_,8,8] ->
    upsampled feature map size: [N,_,16,16]
    So we choose bilinear upsample which supports arbitrary output sizes.
    """
    _, _, H, W = y.size()
    return F.interpolate(x, size=(H, W), mode='bilinear', align_corners=True) + y