Self-Correction-Human-Parsing/networks/backbone/mobilenetv2.py

#!/usr/bin/env python
# -*- encoding: utf-8 -*-

"""
@Author  :   Peike Li
@Contact :   [email protected]
@File    :   mobilenetv2.py
@Time    :   8/4/19 3:35 PM
@Desc    :   
@License :   This source code is licensed under the license found in the 
             LICENSE file in the root directory of this source tree.
"""

import torch.nn as nn
import math
import functools

from modules import InPlaceABN, InPlaceABNSync

BatchNorm2d = functools.partial(InPlaceABNSync, activation='none')

__all__ = ['mobilenetv2']


def conv_bn(inp, oup, stride):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )


def conv_1x1_bn(inp, oup):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        BatchNorm2d(oup),
        nn.ReLU6(inplace=True)
    )


class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        assert stride in [1, 2]

        hidden_dim = round(inp * expand_ratio)
        self.use_res_connect = self.stride == 1 and inp == oup

        if expand_ratio == 1:
            self.conv = nn.Sequential(
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                BatchNorm2d(oup),
            )
        else:
            self.conv = nn.Sequential(
                # pw
                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
                BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # dw
                nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False),
                BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=True),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                BatchNorm2d(oup),
            )

    def forward(self, x):
        if self.use_res_connect:
            return x + self.conv(x)
        else:
            return self.conv(x)


class MobileNetV2(nn.Module):
    def __init__(self, n_class=1000, input_size=224, width_mult=1.):
        super(MobileNetV2, self).__init__()
        block = InvertedResidual
        input_channel = 32
        last_channel = 1280
        interverted_residual_setting = [
            # t, c, n, s
            [1, 16, 1, 1],
            [6, 24, 2, 2],  # layer 2
            [6, 32, 3, 2],  # layer 3
            [6, 64, 4, 2],
            [6, 96, 3, 1],  # layer 4
            [6, 160, 3, 2],
            [6, 320, 1, 1],  # layer 5
        ]

        # building first layer
        assert input_size % 32 == 0
        input_channel = int(input_channel * width_mult)
        self.last_channel = int(last_channel * width_mult) if width_mult > 1.0 else last_channel
        self.features = [conv_bn(3, input_channel, 2)]
        # building inverted residual blocks
        for t, c, n, s in interverted_residual_setting:
            output_channel = int(c * width_mult)
            for i in range(n):
                if i == 0:
                    self.features.append(block(input_channel, output_channel, s, expand_ratio=t))
                else:
                    self.features.append(block(input_channel, output_channel, 1, expand_ratio=t))
                input_channel = output_channel
        # building last several layers
        self.features.append(conv_1x1_bn(input_channel, self.last_channel))
        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)

        # building classifier
        self.classifier = nn.Sequential(
            nn.Dropout(0.2),
            nn.Linear(self.last_channel, n_class),
        )

        self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = x.mean(3).mean(2)
        x = self.classifier(x)
        return x

    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, 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 mobilenetv2(pretrained=False, **kwargs):
    """Constructs a MobileNet_V2 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = MobileNetV2(n_class=1000, **kwargs)
    if pretrained:
        model.load_state_dict(load_url(model_urls['mobilenetv2']), strict=False)
    return model