pytorch_预训练vggm_自定义类别数量_源码分享

系列文章目录

9种经典图片分类卷积模型系列合集（推荐程度依次递减）：

1. Se_resnet50
2. Resnet50
3. Xception
4. inceptionresnetv2
5. resnext
6. bninception
7. shufflenetv2
8. polynet
9. vggm

Imagenet的预训练vggm是1000个类别，根据笔者添加了一个bottleneck层和一个head层使得可以进行自定义类别训练。

源码

from __future__ import print_function, division, absolute_import
import torch
import torch.nn as nn
from torch.autograd import Variable
# from torch.legacy import nn as nnl
import torch.utils.model_zoo as model_zoo

__all__ = ['vggm']

pretrained_settings = {
    'vggm': {
        True: {
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/vggm-786f2434.pth',
            'input_space': 'BGR',
            'input_size': [3, 221, 221],
            'input_range': [0, 255],
            'mean': [123.68, 116.779, 103.939],
            'std': [1, 1, 1],
            'num_classes': 1000
        }
    }
}


def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation)


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
    expansion = 1
    __constants__ = ['downsample']

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

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

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

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

        out += identity
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4
    __constants__ = ['downsample']

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.)) * groups

        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = 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:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out


class SpatialCrossMapLRN(nn.Module):
    def __init__(self, local_size=1, alpha=1.0, beta=0.75, k=1, ACROSS_CHANNELS=True):
        super(SpatialCrossMapLRN, self).__init__()
        self.ACROSS_CHANNELS = ACROSS_CHANNELS
        if ACROSS_CHANNELS:
            self.average = nn.AvgPool3d(kernel_size=(local_size, 1, 1),
                                        stride=1,
                                        padding=(int((local_size - 1.0) / 2), 0, 0))
        else:
            self.average = nn.AvgPool2d(kernel_size=local_size,
                                        stride=1,
                                        padding=int((local_size - 1.0) / 2))
        self.alpha = alpha
        self.beta = beta
        self.k = k

    def forward(self, x):
        if self.ACROSS_CHANNELS:
            div = x.pow(2).unsqueeze(1)
            div = self.average(div).squeeze(1)
            div = div.mul(self.alpha).add(self.k).pow(self.beta)
        else:
            div = x.pow(2)
            div = self.average(div)
            div = div.mul(self.alpha).add(self.k).pow(self.beta)
        x = x.div(div)
        return x


class LambdaBase(nn.Sequential):
    def __init__(self, fn, *args):
        super(LambdaBase, self).__init__(*args)
        self.lambda_func = fn

    def forward_prepare(self, input):
        output = []
        for module in self._modules.values():
            output.append(module(input))
        return output if output else input


class Lambda(LambdaBase):
    def forward(self, input):
        return self.lambda_func(self.forward_prepare(input))


class VGGM(nn.Module):

    def __init__(self, num_classes=1000, zero_init_residual=False):
        super(VGGM, self).__init__()
        self.num_classes = num_classes
        self.features = nn.Sequential(
            nn.Conv2d(3, 96, (7, 7), (2, 2)),
            nn.ReLU(),
            SpatialCrossMapLRN(5, 0.0005, 0.75, 2),
            nn.MaxPool2d((3, 3), (2, 2), (0, 0), ceil_mode=True),
            nn.Conv2d(96, 256, (5, 5), (2, 2), (1, 1)),
            nn.ReLU(),
            SpatialCrossMapLRN(5, 0.0005, 0.75, 2),
            nn.MaxPool2d((3, 3), (2, 2), (0, 0), ceil_mode=True),
            nn.Conv2d(256, 512, (3, 3), (1, 1), (1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, (3, 3), (1, 1), (1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, (3, 3), (1, 1), (1, 1)),
            nn.ReLU(),
            nn.MaxPool2d((3, 3), (2, 2), (0, 0), ceil_mode=True)
        )
        self.classif = nn.Sequential(
            nn.Linear(18432, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(4096, 2048),
        )
        self.bottleneck = nn.Sequential(
            nn.Linear(2048, 512),
            nn.BatchNorm1d(512),
            nn.ReLU(),
            nn.Dropout(0.5)
        )
        self.bottleneck[0].weight.data.normal_(0, 0.005)
        self.bottleneck[0].bias.data.fill_(0.1)
        self.head = nn.Sequential(
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(512, num_classes)
        )
        # self.fc = nn.Linear(512, num_classes)
        for dep in range(2):
            self.head[dep * 3].weight.data.normal_(0, 0.01)
            self.head[dep * 3].bias.data.fill_(0.0)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        x = self.classif(x)
        x = self.bottleneck(x)
        x = self.head(x)
        return x


def vggm(num_classes=1000, pretrained='imagenet'):
    if pretrained:
        settings = pretrained_settings['vggm'][pretrained]
        # assert num_classes == settings['num_classes'], \
        #     "num_classes should be {}, but is {}".format(settings['num_classes'], num_classes)

        model = VGGM(num_classes=1000)
        model.load_state_dict(model_zoo.load_url(settings['url']),strict=False)

        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']
    else:
        model = VGGM(num_classes=num_classes)
    return model