custom_models.py

# Same models as from pytorch
# https://github.com/pytorch/vision/tree/master/torchvision/models
# With generic input for FC instead of hard coded value

import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import math

model_urls = {
    'alexnet': 'https://download.pytorch.org/models/alexnet-owt-4df8aa71.pth',
}

class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, inputs):
        x = self.features(inputs)
        x = x.view(x.size(0), self.classifier[1].in_features)
        x = self.classifier(x)
        return x

class LeNet5(nn.Module):

    def __init__(self, num_classes=10):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(1, 6, kernel_size=5),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(6, 16, kernel_size=5),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(16, 120, kernel_size=5),
            nn.ReLU(inplace=True)
        )
        self.classifier = nn.Sequential(
            nn.Linear(120, 84),
            nn.ReLU(inplace=True),
            nn.Linear(84, 10)
        )

    def forward(self, inputs):
        x = self.features(inputs)
        x = x.view(x.size(0), self.classifier[1].in_features)
        x = self.classifier(x)
        x = nn.LogSoftmax(dim=-1)
        return x

def alexnet(pretrained=False, **kwargs):
    r"""AlexNet model architecture from the
    `"One weird trick..." <https://arxiv.org/abs/1404.5997>`_ paper.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = AlexNet(**kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['alexnet']))
    return model



cfg = {
    'VGG11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'VGG13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'VGG16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'VGG19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'A'],
}

__all__ = ["VGG_CIFAR"]

class LeNet5(nn.Module):

    def __init__(self):
        super(LeNet5, self).__init__()

        self.features = nn.Sequential(
            nn.Conv2d(1, 6, kernel_size=(5, 5)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2)),
            nn.Conv2d(6, 16, kernel_size=(5, 5)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2)),
            nn.Conv2d(16, 120, kernel_size=(5, 5)),
            nn.ReLU()
        )

        self.classifier = nn.Sequential(
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, 10),
            nn.LogSoftmax(dim=-1)
        )

    def forward(self, img):
        output = self.features(img)
        output = output.view(img.size(0), self.classifier[0].in_features)
        output = self.classifier(output)
        return output

class VGG_CIFAR(nn.Module):

    def __init__(self, depth=19, num_classes=10):
        super(VGG_CIFAR, self).__init__()
        self.cfg = cfg['VGG' + str(depth)]
        self.features = self.make_layers(self.cfg)
        self.classifier = nn.Linear(512, num_classes)
        self._initialize_weights()

    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 make_layers(self, cfg):
        layers = []
        in_channels = 3
        for v in cfg:
            if v == 'M':
                layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
            elif v == 'A':
                layers += [nn.AvgPool2d(kernel_size=2, stride=2)]
            else:
                conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
                in_channels = v

        return nn.Sequential(*layers)

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