MSGCoOp/Dassl.ProGrad.pytorch/dassl/modeling/backbone/mobilenetv2.py

import torch.utils.model_zoo as model_zoo
from torch import nn

from .build import BACKBONE_REGISTRY
from .backbone import Backbone

model_urls = {
    "mobilenet_v2":
    "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth",
}


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


class ConvBNReLU(nn.Sequential):

    def __init__(
        self, in_planes, out_planes, kernel_size=3, stride=1, groups=1
    ):
        padding = (kernel_size-1) // 2
        super().__init__(
            nn.Conv2d(
                in_planes,
                out_planes,
                kernel_size,
                stride,
                padding,
                groups=groups,
                bias=False,
            ),
            nn.BatchNorm2d(out_planes),
            nn.ReLU6(inplace=True),
        )


class InvertedResidual(nn.Module):

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

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

        layers = []
        if expand_ratio != 1:
            # pw
            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1))
        layers.extend(
            [
                # dw
                ConvBNReLU(
                    hidden_dim, hidden_dim, stride=stride, groups=hidden_dim
                ),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            ]
        )
        self.conv = nn.Sequential(*layers)

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


class MobileNetV2(Backbone):

    def __init__(
        self,
        width_mult=1.0,
        inverted_residual_setting=None,
        round_nearest=8,
        block=None,
    ):
        """
        MobileNet V2.

        Args:
            width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
            inverted_residual_setting: Network structure
            round_nearest (int): Round the number of channels in each layer to be a multiple of this number
            Set to 1 to turn off rounding
            block: Module specifying inverted residual building block for mobilenet
        """
        super().__init__()

        if block is None:
            block = InvertedResidual
        input_channel = 32
        last_channel = 1280

        if inverted_residual_setting is None:
            inverted_residual_setting = [
                # 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],
            ]

        # only check the first element, assuming user knows t,c,n,s are required
        if (
            len(inverted_residual_setting) == 0
            or len(inverted_residual_setting[0]) != 4
        ):
            raise ValueError(
                "inverted_residual_setting should be non-empty "
                "or a 4-element list, got {}".
                format(inverted_residual_setting)
            )

        # building first layer
        input_channel = _make_divisible(
            input_channel * width_mult, round_nearest
        )
        self.last_channel = _make_divisible(
            last_channel * max(1.0, width_mult), round_nearest
        )
        features = [ConvBNReLU(3, input_channel, stride=2)]
        # building inverted residual blocks
        for t, c, n, s in inverted_residual_setting:
            output_channel = _make_divisible(c * width_mult, round_nearest)
            for i in range(n):
                stride = s if i == 0 else 1
                features.append(
                    block(
                        input_channel, output_channel, stride, expand_ratio=t
                    )
                )
                input_channel = output_channel
        # building last several layers
        features.append(
            ConvBNReLU(input_channel, self.last_channel, kernel_size=1)
        )
        # make it nn.Sequential
        self.features = nn.Sequential(*features)

        self._out_features = self.last_channel

        # weight initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode="fan_out")
                if m.bias is not None:
                    nn.init.zeros_(m.bias)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.ones_(m.weight)
                nn.init.zeros_(m.bias)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.zeros_(m.bias)

    def _forward_impl(self, x):
        # This exists since TorchScript doesn't support inheritance, so the superclass method
        # (this one) needs to have a name other than `forward` that can be accessed in a subclass
        x = self.features(x)
        x = x.mean([2, 3])
        return x

    def forward(self, x):
        return self._forward_impl(x)


def init_pretrained_weights(model, model_url):
    """Initializes model with pretrained weights.

    Layers that don't match with pretrained layers in name or size are kept unchanged.
    """
    if model_url is None:
        import warnings

        warnings.warn(
            "ImageNet pretrained weights are unavailable for this model"
        )
        return
    pretrain_dict = model_zoo.load_url(model_url)
    model_dict = model.state_dict()
    pretrain_dict = {
        k: v
        for k, v in pretrain_dict.items()
        if k in model_dict and model_dict[k].size() == v.size()
    }
    model_dict.update(pretrain_dict)
    model.load_state_dict(model_dict)


@BACKBONE_REGISTRY.register()
def mobilenetv2(pretrained=True, **kwargs):
    model = MobileNetV2(**kwargs)
    if pretrained:
        init_pretrained_weights(model, model_urls["mobilenet_v2"])
    return model