SE+Resnet的backbone的预训练权重

权重下载网址：https://data.lip6.fr/cadene/pretrainedmodels/

  
"""
ResNet code gently borrowed from
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
"""
import os
from collections import OrderedDict
import math

import torch.nn as nn
import torch


pretrained_settings = {
    'se_resnext50_32x4d': {
        'imagenet': {
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext50_32x4d-a260b3a4.pth',
            'input_space': 'RGB',
            'input_size': [3, 224, 224],
            'input_range': [0, 1],
            'mean': [0.485, 0.456, 0.406],
            'std': [0.229, 0.224, 0.225],
            'num_classes': 1000
        }
    },
    'se_resnext101_32x4d': {
        'imagenet': {
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth',
            'input_space': 'RGB',
            'input_size': [3, 224, 224],
            'input_range': [0, 1],
            'mean': [0.485, 0.456, 0.406],
            'std': [0.229, 0.224, 0.225],
            'num_classes': 1000
        }
    },
}


class SEModule(nn.Module):

    def __init__(self, channels, reduction):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc1 = nn.Conv2d(channels, channels // reduction, kernel_size=1,
                             padding=0)
        self.relu = nn.ReLU(inplace=True)
        self.fc2 = nn.Conv2d(channels // reduction, channels, kernel_size=1,
                             padding=0)
        self.sigmoid = nn.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 = self.sigmoid(x)
        return module_input * x


class Bottleneck(nn.Module):
    """
    Base class for bottlenecks that implements `forward()` method.
    """
    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out = self.se_module(out) + residual
        out = self.relu(out)

        return out


class SEResNeXtBottleneck(Bottleneck):
    """
    ResNeXt bottleneck type C with a Squeeze-and-Excitation module.
    """
    expansion = 4

    def __init__(self, inplanes, planes, groups, reduction, stride=1,
                 downsample=None, base_width=4):
        super(SEResNeXtBottleneck, self).__init__()
        width = math.floor(planes * (base_width / 64)) * groups
        self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, bias=False,
                               stride=1)
        self.bn1 = nn.BatchNorm2d(width)
        self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride,
                               padding=1, groups=groups, bias=False)
        self.bn2 = nn.BatchNorm2d(width)
        self.conv3 = nn.Conv2d(width, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.se_module = SEModule(planes * 4, reduction=reduction)
        self.downsample = downsample
        self.stride = stride


class BackBone(nn.Module):

    def __init__(self, block, layers, groups, reduction, dropout_p=0.2,
                 inplanes=128, input_3x3=True, downsample_kernel_size=3,
                 downsample_padding=1):
        """
        Parameters
        ----------
        block (nn.Module): Bottleneck class.
            - For SE-ResNeXt models:  SEResNeXtBottleneck
        layers (list of ints): Number of residual blocks for 4 layers of the
            network (layer1...layer4).
        groups (int): Number of groups for the 3x3 convolution in each
            bottleneck block.
            - For BackBone154: 64
            - For SE-ResNet models: 1
            - For SE-ResNeXt models:  32
        reduction (int): Reduction ratio for Squeeze-and-Excitation modules.
            - For all models: 16
        dropout_p (float or None): Drop probability for the Dropout layer.
            If `None` the Dropout layer is not used.
            - For BackBone154: 0.2
            - For SE-ResNet models: None
            - For SE-ResNeXt models: None
        inplanes (int):  Number of input channels for layer1.
            - For BackBone154: 128
            - For SE-ResNet models: 64
            - For SE-ResNeXt models: 64
        input_3x3 (bool): If `True`, use three 3x3 convolutions instead of
            a single 7x7 convolution in layer0.
            - For BackBone154: True
            - For SE-ResNet models: False
            - For SE-ResNeXt models: False
        downsample_kernel_size (int): Kernel size for downsampling convolutions
            in layer2, layer3 and layer4.
            - For BackBone154: 3
            - For SE-ResNet models: 1
            - For SE-ResNeXt models: 1
        downsample_padding (int): Padding for downsampling convolutions in
            layer2, layer3 and layer4.
            - For BackBone154: 1
            - For SE-ResNet models: 0
            - For SE-ResNeXt models: 0
        num_classes (int): Number of outputs in `last_linear` layer.
            - For all models: 1000
        """
        super(BackBone, self).__init__()
        self.inplanes = inplanes
        if input_3x3:
            layer0_modules = [
                ('conv1', nn.Conv2d(3, 64, 3, stride=2, padding=1,
                                    bias=False)),
                ('bn1', nn.BatchNorm2d(64)),
                ('relu1', nn.ReLU(inplace=True)),
                ('conv2', nn.Conv2d(64, 64, 3, stride=1, padding=1,
                                    bias=False)),
                ('bn2', nn.BatchNorm2d(64)),
                ('relu2', nn.ReLU(inplace=True)),
                ('conv3', nn.Conv2d(64, inplanes, 3, stride=1, padding=1,
                                    bias=False)),
                ('bn3', nn.BatchNorm2d(inplanes)),
                ('relu3', nn.ReLU(inplace=True)),
            ]
        else:
            layer0_modules = [
                ('conv1', nn.Conv2d(3, inplanes, kernel_size=7, stride=2,
                                    padding=3, bias=False)),
                ('bn1', nn.BatchNorm2d(inplanes)),
                ('relu1', nn.ReLU(inplace=True)),
            ]
        # To preserve compatibility with Caffe weights `ceil_mode=True`
        # is used instead of `padding=1`.
        layer0_modules.append(('pool', nn.MaxPool2d(3, stride=2,
                                                    ceil_mode=True)))
        self.layer0 = nn.Sequential(OrderedDict(layer0_modules))
        self.layer1 = self._make_layer(
            block,
            planes=64,
            blocks=layers[0],
            groups=groups,
            reduction=reduction,
            downsample_kernel_size=1,
            downsample_padding=0
        )
        self.layer2 = self._make_layer(
            block,
            planes=128,
            blocks=layers[1],
            stride=2,
            groups=groups,
            reduction=reduction,
            downsample_kernel_size=downsample_kernel_size,
            downsample_padding=downsample_padding
        )
        self.layer3 = self._make_layer(
            block,
            planes=256,
            blocks=layers[2],
            stride=2,
            groups=groups,
            reduction=reduction,
            downsample_kernel_size=downsample_kernel_size,
            downsample_padding=downsample_padding
        )
        self.layer4 = self._make_layer(
            block,
            planes=512,
            blocks=layers[3],
            stride=2,
            groups=groups,
            reduction=reduction,
            downsample_kernel_size=downsample_kernel_size,
            downsample_padding=downsample_padding
        )

    def _make_layer(self, block, planes, blocks, groups, reduction, stride=1,
                    downsample_kernel_size=1, downsample_padding=0):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=downsample_kernel_size, stride=stride,
                          padding=downsample_padding, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, groups, reduction, stride,
                            downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, groups, reduction))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.layer0(x)
        C2 = self.layer1(x)
        C3 = self.layer2(C2)
        C4 = self.layer3(C3)
        C5 = self.layer4(C4)
        return [C3, C4, C5]


def initialize_pretrained_model(model, settings):
    weights_path = os.path.join(os.path.join(os.path.dirname(__file__), '..',
                                        'pretrainedmodels', os.path.basename(settings['url'])))
    state_dict = torch.load(weights_path)
    # filter out last layer
    for layer in ['last_linear.weight', 'last_linear.bias']:
        del state_dict[layer]
    state_dict_cur = model.state_dict()
    state_dict_cur.update(state_dict_cur)

    model.load_state_dict(state_dict_cur)
    model.input_space = settings['input_space']
    model.input_size = settings['input_size']
    model.input_range = settings['input_range']
    model.mean = settings['mean']
    model.std = settings['std']


def se_resnext50_32x4d(pretrained_imagenet):
    model = BackBone(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
                  dropout_p=None, inplanes=64, input_3x3=False,
                  downsample_kernel_size=1, downsample_padding=0,
                  )
    if pretrained_imagenet:
        settings = pretrained_settings['se_resnext50_32x4d']['imagenet']
        initialize_pretrained_model(model, settings)
    return model


def se_resnext101_32x4d(pretrained_imagenet):
    model = BackBone(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
                  dropout_p=None, inplanes=64, input_3x3=False,
                  downsample_kernel_size=1, downsample_padding=0,
                  )
    if pretrained_imagenet:
        settings = pretrained_settings['se_resnext101_32x4d']['imagenet']
        initialize_pretrained_model(model, settings)
    return model