squeezenet.py

# flake8: noqa

import keras  # work around segfault
import sys
import numpy as np
import math

import torch
import torchvision
import torch.nn as nn
from torch.autograd import Variable

from pytorch2keras.converter import pytorch_to_keras

# The code from torchvision
import math
import torch
import torch.nn as nn
import torch.nn.init as init


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):
        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=False),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=False),
                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=False),
                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=False),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=False),
                Fire(128, 32, 128, 128),
                Fire(256, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=False),
                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=0.5),
            final_conv,
            nn.ReLU(inplace=True),
            nn.AvgPool2d(13, stride=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)
        x = self.classifier(x)
        return x.view(x.size(0), self.num_classes)


if __name__ == '__main__':
    max_error = 0
    for i in range(10):
        model = SqueezeNet(version=1.1)
        for m in model.modules():
            m.training = False

        input_np = np.random.uniform(0, 1, (1, 3, 224, 224))
        input_var = Variable(torch.FloatTensor(input_np))
        output = model(input_var)

        k_model = pytorch_to_keras(model, input_var, (3, 224, 224,), verbose=True)

        pytorch_output = output.data.numpy()
        keras_output = k_model.predict(input_np)

        error = np.max(pytorch_output - keras_output)
        print(error)
        if max_error < error:
            max_error = error

    print('Max error: {0}'.format(max_error))