Dassl.pytorch/dassl/modeling/backbone/vgg.py

import torch
import torch.nn as nn

from .build import BACKBONE_REGISTRY
from .backbone import Backbone

try:
    from torch.hub import load_state_dict_from_url
except ImportError:
    from torch.utils.model_zoo import load_url as load_state_dict_from_url

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",
    "vgg11_bn": "https://download.pytorch.org/models/vgg11_bn-6002323d.pth",
    "vgg13_bn": "https://download.pytorch.org/models/vgg13_bn-abd245e5.pth",
    "vgg16_bn": "https://download.pytorch.org/models/vgg16_bn-6c64b313.pth",
    "vgg19_bn": "https://download.pytorch.org/models/vgg19_bn-c79401a0.pth",
}


class VGG(Backbone):

    def __init__(self, features, init_weights=True):
        super().__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        # Note that self.classifier outputs features rather than logits
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
        )

        self._out_features = 4096

        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        return self.classifier(x)

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(
                    m.weight, mode="fan_out", nonlinearity="relu"
                )
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)


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)


cfgs = {
    "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 _vgg(arch, cfg, batch_norm, pretrained):
    init_weights = False if pretrained else True
    model = VGG(
        make_layers(cfgs[cfg], batch_norm=batch_norm),
        init_weights=init_weights
    )
    if pretrained:
        state_dict = load_state_dict_from_url(model_urls[arch], progress=True)
        model.load_state_dict(state_dict, strict=False)
    return model


@BACKBONE_REGISTRY.register()
def vgg16(pretrained=True, **kwargs):
    return _vgg("vgg16", "D", False, pretrained)