import torch.nn as nn

__all__ = ['mobile_v2']


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


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


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(
                nn.Conv2d(hidden_dim,
                          hidden_dim,
                          3,
                          stride,
                          1,
                          groups=hidden_dim,
                          bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=False),
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup),
            )
        else:
            self.conv = nn.Sequential(
                nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=False),
                nn.Conv2d(hidden_dim,
                          hidden_dim,
                          3,
                          stride,
                          1,
                          groups=hidden_dim,
                          bias=False),
                nn.BatchNorm2d(hidden_dim),
                nn.ReLU6(inplace=False),
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                nn.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,
                 scale=1,
                 num_classes=1000,
                 input_size=224,
                 width_mult=1.):
        super(MobileNetV2, self).__init__()
        block = InvertedResidual
        input_channel = 32
        last_channel = 1280
        interverted_residual_setting = [
            [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],
        ]

        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)]
        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
        self.features.append(conv_1x1_bn(input_channel, self.last_channel))
        self.features = nn.Sequential(*self.features)

        self.classifier = nn.Sequential(
            nn.Dropout(0.2),
            # nn.Conv2d(self.last_channel, num_classes, kernel_size=1))
            nn.Linear(self.last_channel, num_classes))

        self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = x.mean(3).mean(2)
        x = self.classifier(x)
        # x = x.view(x.size(0), -1)
        return x

    def _initialize_weights(self):
        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:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, std=0.001)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)


def mobile_v2(**kwargs):
    model = MobileNetV2(**kwargs)
    return model