Vgg16_BN.py

import torch
import torch.nn as nn
from typing import cast

__all__ = ["Vgg_16_bn"]

def make_layers(cfg, batch_norm):
    layers: List[nn.Module] = []
    in_channels = 3
    for v in cfg:
        if v == "M":
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            v = cast(int, v)
            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)



class Vgg_16_bn(nn.Module):
    def __init__(self, num_classes = 3, dropout = 0.5):
        super().__init__()
        
        cfg = [64, 64, "M", 128, 128, "M", 256, 256, 256, "M", 512, 512, 512, "M", 512, 512, 512, "M"]
        
        self.features = make_layers(cfg, batch_norm=True)
        
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(p=dropout),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(p=dropout),
            nn.Linear(4096, num_classes),
        )
        
        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 forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x


if __name__ == "__main__":
    model = Vgg_16_bn()
    input = torch.randn(1,3,224,224)
    output = model(input)
    print(input.size(), output.size())
    assert output.size()[-1] == 3
    print("Model done")