vgg.py

import math

import torch.nn as nn
import torch.utils.model_zoo as model_zoo
from torch.nn.parameter import Parameter

__all__ = [
    'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
    'vgg19_bn', 'vgg19',
]

model_urls = {
    'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
    'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
}

'''
VGG module privdes simple interface to generate different versions of VGG
models.
'''
class VGG(nn.Module):
    '''
    class : VGG
    '''
    def __init__(self, features, num_classes=1000):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
        )
        self.final = nn.Linear(4096, num_classes)
        self._initialize_weights()

    def forward(self, img):
        '''
        forward propagation.
        img : input image
        '''
        conv_feature = self.features(img)
        fc_feature = conv_feature.view(conv_feature.size(0), -1)
        last_feature = self.classifier(fc_feature)
        prediction = self.final(last_feature)
        return prediction

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                n = m.weight.size(1)
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()

    def load_pretrained_model(self, state_dict):
        """
        Modified from load_state_dict function
        This function tries to load the classification model pre-trained on ImageNet
        Arguments:
            state_dict (dict): A dict containing parameters and
                persistent buffers.
        """
        own_state = self.state_dict()
        for name, param in state_dict.items():
            if name not in own_state:
                print "=>{} is in the pretrained model, but not in the current model".format(name)
                continue
            print "=> loading {}".format(name)
            if isinstance(param, Parameter):
                # backwards compatibility for serialized parameters
                param = param.data
            own_state[name].copy_(param)

        missing = set(own_state.keys()) - set(state_dict.keys())
        print ("The following parameters are not set by the pre-trained model:", missing)


def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


cfg = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def vgg11(pretrained=False, **kwargs):
    """VGG 11-layer model (configuration "A")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = VGG(make_layers(cfg['A']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg11']))
    return model


def vgg11_bn(**kwargs):
    """VGG 11-layer model (configuration "A") with batch normalization"""
    return VGG(make_layers(cfg['A'], batch_norm=True), **kwargs)


def vgg13(pretrained=False, **kwargs):
    """VGG 13-layer model (configuration "B")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = VGG(make_layers(cfg['B']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg13']))
    return model


def vgg13_bn(**kwargs):
    """VGG 13-layer model (configuration "B") with batch normalization"""
    return VGG(make_layers(cfg['B'], batch_norm=True), **kwargs)


def vgg16(pretrained=False, **kwargs):
    """VGG 16-layer model (configuration "D")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = VGG(make_layers(cfg['D']), **kwargs)
    if pretrained:
        model.load_pretrained_model(model_zoo.load_url(model_urls['vgg16']))
    return model


def vgg16_bn(**kwargs):
    """VGG 16-layer model (configuration "D") with batch normalization"""
    return VGG(make_layers(cfg['D'], batch_norm=True), **kwargs)


def vgg19(pretrained=False, **kwargs):
    """VGG 19-layer model (configuration "E")

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = VGG(make_layers(cfg['E']), **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['vgg19']))
    return model


def vgg19_bn(**kwargs):
    """VGG 19-layer model (configuration 'E') with batch normalization"""
    return VGG(make_layers(cfg['E'], batch_norm=True), **kwargs)