squeezenet.py

import math
import numpy as np
import torch
import torch.nn as nn
import torch.nn.init as init
import torch.utils.model_zoo as model_zoo


__all__ = ['SqueezeNet', 'squeezenet1_0', 'squeezenet1_1']


model_urls = {
    'squeezenet1_0': 'https://download.pytorch.org/models/squeezenet1_0-a815701f.pth',
    'squeezenet1_1': 'https://download.pytorch.org/models/squeezenet1_1-f364aa15.pth',
}


class Fire(nn.Module):

    def __init__(self, inplanes, squeeze_planes,
                 expand1x1_planes, expand3x3_planes):
        super(Fire, self).__init__()
        self.inplanes = inplanes
        self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes,
                                   kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes,
                                   kernel_size=3, padding=1)
        self.expand3x3_activation = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.squeeze_activation(self.squeeze(x))
        return torch.cat([
            self.expand1x1_activation(self.expand1x1(x)),
            self.expand3x3_activation(self.expand3x3(x))
        ], 1)


class SqueezeNet(nn.Module):

    def __init__(self, version=1.0, num_classes=1000,dropout_factor = 1.):
        super(SqueezeNet, self).__init__()
        if version not in [1.0, 1.1]:
            raise ValueError("Unsupported SqueezeNet version {version}:"
                             "1.0 or 1.1 expected".format(version=version))
        self.num_classes = num_classes
        if version == 1.0:
            self.features = nn.Sequential(
                nn.Conv2d(3, 96, kernel_size=7, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 32, 128, 128),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(512, 64, 256, 256),
            )
        else:
            self.features = nn.Sequential(
                nn.Conv2d(3, 64, kernel_size=3, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(128, 32, 128, 128),
                Fire(256, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                Fire(512, 64, 256, 256),
            )
        # Final convolution is initialized differently form the rest
        final_conv = nn.Conv2d(512, self.num_classes, kernel_size=1)
        self.classifier = nn.Sequential(
            nn.Dropout(p=dropout_factor),
            final_conv,
            nn.ReLU(inplace=True),
            nn.AdaptiveAvgPool2d(1)
        )

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                if m is final_conv:
                    init.normal(m.weight.data, mean=0.0, std=0.01)
                else:
                    init.kaiming_uniform(m.weight.data)
                if m.bias is not None:
                    m.bias.data.zero_()

    def forward(self, x):
        x = self.features(x)
        # print("features(x):", x.size())
        x = self.classifier(x)
        # print("features(x):", x.size())
        return x.view(x.size(0), self.num_classes)


def squeezenet1_0(pretrained=False, **kwargs):
    r"""SqueezeNet model architecture from the `"SqueezeNet: AlexNet-level
    accuracy with 50x fewer parameters and <0.5MB model size"
    <https://arxiv.org/abs/1602.07360>`_ paper.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = SqueezeNet(version=1.0, **kwargs)
    model_dict = model.state_dict()
    if pretrained:
        pretrained_state_dict = model_zoo.load_url(model_urls['squeezenet1_0'])
        pretrained_dict = {k: v for k, v in pretrained_state_dict.items() if
                       k in model_dict and model_dict[k].size() == pretrained_state_dict[k].size()}
        model.load_state_dict(pretrained_dict,strict=False)
    return model


def squeezenet1_1(pretrained=False, **kwargs):
    r"""SqueezeNet 1.1 model from the `official SqueezeNet repo
    <https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1>`_.
    SqueezeNet 1.1 has 2.4x less computation and slightly fewer parameters
    than SqueezeNet 1.0, without sacrificing accuracy.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = SqueezeNet(version=1.1, **kwargs)
    model_dict = model.state_dict()
    if pretrained:
        pretrained_state_dict = model_zoo.load_url(model_urls['squeezenet1_0'])
        pretrained_dict = {k: v for k, v in pretrained_state_dict.items() if
                       k in model_dict and model_dict[k].size() == pretrained_state_dict[k].size()}
        model.load_state_dict(pretrained_dict,strict=False)
    return model


if __name__ == "__main__":
    from thop import profile
    dummy = torch.from_numpy(np.random.random([16, 3, 256, 256]).astype(np.float32))
    model = squeezenet1_0(pretrained=True, num_classes=42,dropout_factor = 0.5)
    print(model)
    flops, params = profile(model, inputs=(dummy, ))
    model.eval()
    output = model(dummy)
    print(output.size())
    print("flops: {}, params: {}".format(flops, params))