fast-reid/fastreid/modeling/backbones/mobilenet.py

"""
Creates a MobileNetV2 Model as defined in:
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018).
MobileNetV2: Inverted Residuals and Linear Bottlenecks
arXiv preprint arXiv:1801.04381.
import from https://github.com/tonylins/pytorch-mobilenet-v2
"""
import logging
import math

import torch
import torch.nn as nn

from fastreid.layers import get_norm
from fastreid.utils.checkpoint import get_missing_parameters_message, get_unexpected_parameters_message
from .build import BACKBONE_REGISTRY

logger = logging.getLogger(__name__)


def _make_divisible(v, divisor, min_value=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    :param v:
    :param divisor:
    :param min_value:
    :return:
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v


def conv_3x3_bn(inp, oup, stride, bn_norm):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        get_norm(bn_norm, oup),
        nn.ReLU6(inplace=True)
    )


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


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

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

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


class MobileNetV2(nn.Module):
    def __init__(self, bn_norm, width_mult=1.):
        super(MobileNetV2, self).__init__()
        # setting of inverted residual blocks
        self.cfgs = [
            # t, c, n, s
            [1, 16, 1, 1],
            [6, 24, 2, 2],
            [6, 32, 3, 2],
            [6, 64, 4, 2],
            [6, 96, 3, 1],
            [6, 160, 3, 2],
            [6, 320, 1, 1],
        ]

        # building first layer
        input_channel = _make_divisible(32 * width_mult, 4 if width_mult == 0.1 else 8)
        layers = [conv_3x3_bn(3, input_channel, 2, bn_norm)]
        # building inverted residual blocks
        block = InvertedResidual
        for t, c, n, s in self.cfgs:
            output_channel = _make_divisible(c * width_mult, 4 if width_mult == 0.1 else 8)
            for i in range(n):
                layers.append(block(input_channel, output_channel, bn_norm, s if i == 0 else 1, t))
                input_channel = output_channel
        self.features = nn.Sequential(*layers)
        # building last several layers
        output_channel = _make_divisible(1280 * width_mult, 4 if width_mult == 0.1 else 8) if width_mult > 1.0 else 1280
        self.conv = conv_1x1_bn(input_channel, output_channel, bn_norm)

        self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = self.conv(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, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()


@BACKBONE_REGISTRY.register()
def build_mobilenetv2_backbone(cfg):
    """
    Create a MobileNetV2 instance from config.
    Returns:
        MobileNetV2: a :class: `MobileNetV2` instance.
    """
    # fmt: off
    pretrain      = cfg.MODEL.BACKBONE.PRETRAIN
    pretrain_path = cfg.MODEL.BACKBONE.PRETRAIN_PATH
    bn_norm       = cfg.MODEL.BACKBONE.NORM
    depth         = cfg.MODEL.BACKBONE.DEPTH
    # fmt: on

    width_mult = {
        "1.0x": 1.0,
        "0.75x": 0.75,
        "0.5x": 0.5,
        "0.35x": 0.35,
        '0.25x': 0.25,
        '0.1x': 0.1,
    }[depth]

    model = MobileNetV2(bn_norm, width_mult)

    if pretrain:
        try:
            state_dict = torch.load(pretrain_path, map_location=torch.device('cpu'))
            logger.info(f"Loading pretrained model from {pretrain_path}")
        except FileNotFoundError as e:
            logger.info(f'{pretrain_path} is not found! Please check this path.')
            raise e
        except KeyError as e:
            logger.info("State dict keys error! Please check the state dict.")
            raise e

        incompatible = model.load_state_dict(state_dict, strict=False)
        if incompatible.missing_keys:
            logger.info(
                get_missing_parameters_message(incompatible.missing_keys)
            )
        if incompatible.unexpected_keys:
            logger.info(
                get_unexpected_parameters_message(incompatible.unexpected_keys)
            )

    return model