conveying_belt_recognition/deep-hough-transform-master/model/backbone/mobilenet.py

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

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(ConvBNReLU, self).__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(InvertedResidual, self).__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(nn.Module):
    def __init__(self, pretrained=True):
        """
        MobileNet V2 main class
        Args:
            num_classes (int): Number of classes
            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(MobileNetV2, self).__init__()


        block = InvertedResidual
        input_channel = 32
        last_channel = 1280
        width_mult = 1.0
        round_nearest=8

        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)

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

        self.toplayer = nn.Conv2d(160, 32, kernel_size=1, stride=1, padding=0)

        self.latlayer1 = nn.Conv2d(64, 32, kernel_size=1, stride=1, padding=0)
        self.latlayer2 = nn.Conv2d( 32, 32, kernel_size=1, stride=1, padding=0)
        self.latlayer3 = nn.Conv2d( 24, 32, kernel_size=1, stride=1, padding=0)

        self.smooth1 = nn.Conv2d(32, 32, kernel_size=3, stride=1, padding=1)
        self.smooth2 = nn.Conv2d(32, 32, kernel_size=3, stride=1, padding=1)
        self.smooth3 = nn.Conv2d(32, 32, kernel_size=3, stride=1, padding=1)

        self.fpn_selected = [2, 5, 9, 15]
        # 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)

        if pretrained:
            self._load_pretrained_model()

    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
        fpn_features = []
        for i, f in enumerate(self.features):
            x = f(x)
            if i in self.fpn_selected:
                fpn_features.append(x)
        c2, c3, c4, c5 = fpn_features
         # Top-down
        p5 = self.toplayer(c5)
        p4 = nn.functional.upsample(p5, size=c4.size()[2:], mode='bilinear', align_corners=True) + self.latlayer1(c4)
        p3 = nn.functional.upsample(p4, size=c3.size()[2:], mode='bilinear', align_corners=True) + self.latlayer2(c3)
        p2 = nn.functional.upsample(p3, size=c2.size()[2:], mode='bilinear', align_corners=True) + self.latlayer3(c2)
        
        p4 = self.smooth1(p4)
        p3 = self.smooth2(p3)
        p2 = self.smooth3(p2)
        
        return p2, p3, p4, p5
        # x = self.features(x)
        # Cannot use "squeeze" as batch-size can be 1 => must use reshape with x.shape[0]
        # x = nn.functional.adaptive_avg_pool2d(x, 1).reshape(x.shape[0], -1)
        # x = self.classifier(x)
        # return x

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

    def _load_pretrained_model(self):
        pretrain_dict = model_zoo.load_url('https://download.pytorch.org/models/mobilenet_v2-b0353104.pth')
        model_dict = {}
        state_dict = self.state_dict()
        for k, v in pretrain_dict.items():
            if k in state_dict:
                model_dict[k] = v
        state_dict.update(model_dict)
        self.load_state_dict(state_dict)

def MobileNet_FPN(output_stride=None, BatchNorm=nn.BatchNorm2d, pretrained=True):
    """Constructs a ResNet-101 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = MobileNetV2(pretrained=pretrained)
    return model