import torch
import torch.nn as nn
from torch.nn import functional as F
import math
from utils import stochastic_depth
############# Mobile Net V3 #############
def make_divisible(x, divisible_by=8):
    import numpy as np
    return int(np.ceil(x * 1. / divisible_by) * divisible_by)

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

# without bn
def conv_block(inp, oup, stride, conv_layer=nn.Conv2d, nlin_layer=nn.ReLU):
    return nn.Sequential(
        conv_layer(inp, oup, 3, stride, 1, bias=False),
        nlin_layer(0.1, inplace=True)
    )

def trans_conv_block(inp, oup, stride, conv_layer=nn.ConvTranspose2d, nlin_layer=nn.ReLU):
    return nn.Sequential(
        conv_layer(inp, oup, 2, 2),               #Transpose convolution을 통하여 가로세로 2배로.
        nlin_layer(0.1, inplace=True)
    )

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

class Hswish(nn.Module):
    def __init__(self, inplace=True):
        super(Hswish, self).__init__()
        self.inplace = inplace

    def forward(self, x):
        return x * F.relu6(x + 3., inplace=self.inplace) / 6.


class Hsigmoid(nn.Module):
    def __init__(self, inplace=True):
        super(Hsigmoid, self).__init__()
        self.inplace = inplace

    def forward(self, x):
        return F.relu6(x + 3., inplace=self.inplace) / 6.


class SEModule(nn.Module):
    def __init__(self, channel, reduction=4):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=False),
            Hsigmoid()
            # nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y.expand_as(x)


class Identity(nn.Module):
    def __init__(self, channel):
        super(Identity, self).__init__()

    def forward(self, x):
        return x

class MobileBottleneck(nn.Module):
    def __init__(self, inp, oup, kernel, stride, exp, se=False, nl='RE', stochastic=False, block_ratio=None):
        super(MobileBottleneck, self).__init__()
        assert stride in [1, 2]
        assert kernel in [3, 5]
        padding = (kernel - 1) // 2
        self.use_res_connect = stride == 1 and inp == oup
        self.use_stochastic = stochastic
        self.block_ratio = block_ratio

        conv_layer = nn.Conv2d
        norm_layer = nn.BatchNorm2d
        if nl == 'RE':
            nlin_layer = nn.ReLU # or ReLU6
        elif nl == 'HS':
            nlin_layer = Hswish
        else:
            raise NotImplementedError
        if se:
            SELayer = SEModule
        else:
            SELayer = Identity

        self.conv = nn.Sequential(
            # pw
            conv_layer(inp, exp, 1, 1, 0, bias=False),
            norm_layer(exp),
            nlin_layer(inplace=True),
            # dw
            conv_layer(exp, exp, kernel, stride, padding, groups=exp, bias=False),
            norm_layer(exp),
            SELayer(exp),
            nlin_layer(inplace=True),
            # pw-linear
            conv_layer(exp, oup, 1, 1, 0, bias=False),
            norm_layer(oup),
        )

    def forward(self, x):
        if self.use_res_connect:
            if self.use_stochastic:
                return x + stochastic_depth(self.conv(x),self.training, 0.2 * self.block_ratio)
            else:
                return x + self.conv(x)
        else:
            if self.use_stochastic:
                return stochastic_depth(self.conv(x), self.training, 0.2 * self.block_ratio)
            else:
                return self.conv(x)
    

class MobileNetV3(nn.Module):
    def __init__(self, n_class, input_size=64, dropout=0.8, width_mult=1.0, blocknum=4, stochastic=False):
        super(MobileNetV3, self).__init__()
        input_channel = 16
        last_channel = 1280
        self.mobileblock = [
                # k, exp, c,  se,     nl,  s,
                [3, 16,  16,  True,  'RE', 2],
                [3, 72,  24,  False, 'RE', 2],
                [3, 88,  24,  False, 'RE', 1],
                [5, 96,  40,  True,  'HS', 2],
                [5, 240, 40,  True,  'HS', 1],
                [5, 240, 40,  True,  'HS', 1],
                [5, 120, 48,  True,  'HS', 1],
                [5, 144, 48,  True,  'HS', 1],
                [5, 288, 96,  True,  'HS', 2],
                [5, 576, 96,  True,  'HS', 1],
                [5, 576, 96,  True,  'HS', 1],
            ]

        mobile_setting = [
            self.mobileblock[idx] for idx in range(blocknum)
        ]
        self.last_exp = self.mobileblock[blocknum-1][1]

        # building first layer
        assert input_size % 32 == 0
        last_channel = make_divisible(last_channel * width_mult) if width_mult > 1.0 else last_channel
        self.features = [conv_bn(1, input_channel, 2, nlin_layer=Hswish)]   #input channel change
        self.classifier = []

        # building mobile blocks
        for idx, (k, exp, c, se, nl, s) in enumerate(mobile_setting):
            output_channel = make_divisible(c * width_mult)
            exp_channel = make_divisible(exp * width_mult)
            self.features.append(MobileBottleneck(input_channel, output_channel, k, s, exp_channel, se, nl, stochastic=stochastic, block_ratio=float(idx) / float(blocknum)))
            input_channel = output_channel

        # building last several layers
        last_conv = make_divisible(self.last_exp * width_mult)
        self.features.append(conv_1x1_bn(input_channel, last_conv, nlin_layer=Hswish))
        # self.features.append(SEModule(last_conv))  # refer to paper Table2, but I think this is a mistake
        self.features.append(nn.AdaptiveAvgPool2d(1))
        self.features.append(nn.Conv2d(last_conv, last_channel, 1, 1, 0))
        self.features.append(Hswish(inplace=True))

        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)
        # building classifier
        self.classifier = nn.Sequential(
            nn.Dropout(p=dropout),    # refer to paper section 6
            nn.Linear(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):
        # 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)
                if m.bias is not None:
                    nn.init.zeros_(m.bias)


def mobilenetv3(pretrained=False, **kwargs):
    model = MobileNetV3(**kwargs)
    if pretrained:
        state_dict = torch.load('mobilenetv3_small_67.4.pth.tar')
        model.load_state_dict(state_dict, strict=True)
        # raise NotImplementedError
    return model


### EFFICIENT NET ###
from utils import (
    round_filters,
    round_repeats,
    drop_connect,
    get_same_padding_conv2d,
    get_model_params,
    efficientnet_params,
    load_pretrained_weights,
    Swish,
    MemoryEfficientSwish,
)


class MBConvBlock(nn.Module):
    """
    Mobile Inverted Residual Bottleneck Block
    Args:
        block_args (namedtuple): BlockArgs, see above
        global_params (namedtuple): GlobalParam, see above
    Attributes:
        has_se (bool): Whether the block contains a Squeeze and Excitation layer.
    """

    def __init__(self, block_args, global_params):
        super().__init__()
        self._block_args = block_args
        self._bn_mom = 1 - global_params.batch_norm_momentum
        self._bn_eps = global_params.batch_norm_epsilon
        self.has_se = (self._block_args.se_ratio is not None) and (0 < self._block_args.se_ratio <= 1)
        self.id_skip = block_args.id_skip  # skip connection and drop connect

        # Get static or dynamic convolution depending on image size
        Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)

        # Expansion phase
        inp = self._block_args.input_filters  # number of input channels
        oup = self._block_args.input_filters * self._block_args.expand_ratio  # number of output channels
        if self._block_args.expand_ratio != 1:
            self._expand_conv = Conv2d(in_channels=inp, out_channels=oup, kernel_size=1, bias=False)
            self._bn0 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)

        # Depthwise convolution phase
        k = self._block_args.kernel_size
        s = self._block_args.stride
        self._depthwise_conv = Conv2d(
            in_channels=oup, out_channels=oup, groups=oup,  # groups makes it depthwise
            kernel_size=k, stride=s, bias=False)
        self._bn1 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)

        # Squeeze and Excitation layer, if desired
        if self.has_se:
            num_squeezed_channels = max(1, int(self._block_args.input_filters * self._block_args.se_ratio))
            self._se_reduce = Conv2d(in_channels=oup, out_channels=num_squeezed_channels, kernel_size=1)
            self._se_expand = Conv2d(in_channels=num_squeezed_channels, out_channels=oup, kernel_size=1)

        # Output phase
        final_oup = self._block_args.output_filters
        self._project_conv = Conv2d(in_channels=oup, out_channels=final_oup, kernel_size=1, bias=False)
        self._bn2 = nn.BatchNorm2d(num_features=final_oup, momentum=self._bn_mom, eps=self._bn_eps)
        self._swish = MemoryEfficientSwish()

    def forward(self, inputs, drop_connect_rate=None):
        """
        :param inputs: input tensor
        :param drop_connect_rate: drop connect rate (float, between 0 and 1)
        :return: output of block
        """

        # Expansion and Depthwise Convolution
        x = inputs
        if self._block_args.expand_ratio != 1:
            x = self._swish(self._bn0(self._expand_conv(inputs)))
        x = self._swish(self._bn1(self._depthwise_conv(x)))

        # Squeeze and Excitation
        if self.has_se:
            x_squeezed = F.adaptive_avg_pool2d(x, 1)
            x_squeezed = self._se_expand(self._swish(self._se_reduce(x_squeezed)))
            x = torch.sigmoid(x_squeezed) * x

        x = self._bn2(self._project_conv(x))

        # Skip connection and drop connect
        input_filters, output_filters = self._block_args.input_filters, self._block_args.output_filters
        if self.id_skip and self._block_args.stride == 1 and input_filters == output_filters:
            if drop_connect_rate:
                x = drop_connect(x, p=drop_connect_rate, training=self.training)
            x = x + inputs  # skip connection
        return x

    def set_swish(self, memory_efficient=True):
        """Sets swish function as memory efficient (for training) or standard (for export)"""
        self._swish = MemoryEfficientSwish() if memory_efficient else Swish()


class EfficientNet(nn.Module):
    """
    An EfficientNet model. Most easily loaded with the .from_name or .from_pretrained methods
    Args:
        blocks_args (list): A list of BlockArgs to construct blocks
        global_params (namedtuple): A set of GlobalParams shared between blocks
    Example:
        model = EfficientNet.from_pretrained('efficientnet-b0')
    """

    def __init__(self, blocks_args=None, global_params=None):
        super().__init__()
        assert isinstance(blocks_args, list), 'blocks_args should be a list'
        assert len(blocks_args) > 0, 'block args must be greater than 0'
        self._global_params = global_params
        self._blocks_args = blocks_args

        # Get static or dynamic convolution depending on image size
        Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)

        # Batch norm parameters
        bn_mom = 1 - self._global_params.batch_norm_momentum
        bn_eps = self._global_params.batch_norm_epsilon

        # Stem
        in_channels = 1  # rgb
        out_channels = round_filters(32, self._global_params)  # number of output channels
        self._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
        self._bn0 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)

        # Build blocks
        self._blocks = nn.ModuleList([])
        for block_args in self._blocks_args:

            # Update block input and output filters based on depth multiplier.
            block_args = block_args._replace(
                input_filters=round_filters(block_args.input_filters, self._global_params),
                output_filters=round_filters(block_args.output_filters, self._global_params),
                num_repeat=round_repeats(block_args.num_repeat, self._global_params)
            )

            # The first block needs to take care of stride and filter size increase.
            self._blocks.append(MBConvBlock(block_args, self._global_params))
            if block_args.num_repeat > 1:
                block_args = block_args._replace(input_filters=block_args.output_filters, stride=1)
            for _ in range(block_args.num_repeat - 1):
                self._blocks.append(MBConvBlock(block_args, self._global_params))

        # Head
        in_channels = block_args.output_filters  # output of final block
        out_channels = round_filters(1280, self._global_params)
        self._conv_head = Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
        self._bn1 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)

        # Final linear layer
        self._avg_pooling = nn.AdaptiveAvgPool2d(1)
        self._dropout = nn.Dropout(self._global_params.dropout_rate)
        self._fc = nn.Linear(out_channels, self._global_params.num_classes)
        self._swish = MemoryEfficientSwish()

    def set_swish(self, memory_efficient=True):
        """Sets swish function as memory efficient (for training) or standard (for export)"""
        self._swish = MemoryEfficientSwish() if memory_efficient else Swish()
        for block in self._blocks:
            block.set_swish(memory_efficient)


    def extract_features(self, inputs):
        """ Returns output of the final convolution layer """

        # Stem
        x = self._swish(self._bn0(self._conv_stem(inputs)))

        # Blocks
        for idx, block in enumerate(self._blocks):
            drop_connect_rate = self._global_params.drop_connect_rate
            if drop_connect_rate:
                drop_connect_rate *= float(idx) / len(self._blocks)
            x = block(x, drop_connect_rate=drop_connect_rate)

        # Head
        x = self._swish(self._bn1(self._conv_head(x)))

        return x

    def forward(self, inputs):
        """ Calls extract_features to extract features, applies final linear layer, and returns logits. """
        bs = inputs.size(0)
        # Convolution layers
        x = self.extract_features(inputs)

        # Pooling and final linear layer
        x = self._avg_pooling(x)
        x = x.view(bs, -1)
        x = self._dropout(x)
        x = self._fc(x)
        return x

    @classmethod
    def from_name(cls, model_name, override_params=None):
        cls._check_model_name_is_valid(model_name)
        blocks_args, global_params = get_model_params(model_name, override_params)
        return cls(blocks_args, global_params)

    @classmethod
    def from_pretrained(cls, model_name, advprop=False, num_classes=1000, in_channels=3):
        model = cls.from_name(model_name, override_params={'num_classes': num_classes})
        load_pretrained_weights(model, model_name, load_fc=(num_classes == 1000), advprop=advprop)
        if in_channels != 3:
            Conv2d = get_same_padding_conv2d(image_size = model._global_params.image_size)
            out_channels = round_filters(32, model._global_params)
            model._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
        return model
    
    @classmethod
    def get_image_size(cls, model_name):
        cls._check_model_name_is_valid(model_name)
        _, _, res, _ = efficientnet_params(model_name)
        return res

    @classmethod
    def _check_model_name_is_valid(cls, model_name):
        """ Validates model name. """ 
        valid_models = ['efficientnet-b'+str(i) for i in range(9)]
        if model_name not in valid_models:
            raise ValueError('model_name should be one of: ' + ', '.join(valid_models))

class AutoEncoder(nn.Module):
    def __init__(self, input_channel=1):
        super(AutoEncoder, self).__init__()
        self.input_channel = input_channel
        self.encoder, self.decoder = self.make_encoder_layers()

    def make_encoder_layers(self, input_channel=1,layer_num=6):
        encoder_output_channels = [64,56,48,32,24,20]
        decoder_output_channels = [24,32,48,56,64,1]
        encoder = []
        decoder = []

        #make encoder
        for i in range(layer_num):
            encoder.append(conv_block(input_channel, encoder_output_channels[i], 1, nlin_layer=nn.LeakyReLU))
            encoder.append(conv_block(encoder_output_channels[i], encoder_output_channels[i],1,nlin_layer=nn.LeakyReLU))
            encoder.append(nn.MaxPool2d(2,2))
            if(i != layer_num-1):
                encoder.append(nn.Dropout2d(p=0.3))
            input_channel = encoder_output_channels[i]

        #make decoder
        for i in range(layer_num):
            decoder.append(nn.Upsample(scale_factor=2))
            decoder.append(conv_block(input_channel, input_channel, 1, nlin_layer=nn.LeakyReLU))
            decoder.append(conv_block(input_channel, decoder_output_channels[i], 1, nlin_layer=nn.LeakyReLU))
            if(i != layer_num-1):
                decoder.append(nn.Dropout2d(p=0.3))
            input_channel = decoder_output_channels[i]


        encoder = nn.Sequential(*encoder)
        decoder = nn.Sequential(*decoder)
        return encoder, decoder

    def forward(self, x):
        x = self.encoder(x)
        print(x.shape)
        x = self.decoder(x)
        return x
class AutoEncoder_s(nn.Module):
    def __init__(self, input_channel=1):
        super(AutoEncoder, self).__init__()
        self.input_channel = input_channel
        self.encoder, self.decoder = self.make_encoder_layers()

    def make_encoder_layers(self, input_channel=1,layer_num=3):
        encoder_output_channels = [64,56,48]
        decoder_output_channels = [56,64,1]
        encoder = []
        decoder = []

        #make encoder
        for i in range(layer_num):
            encoder.append(conv_block(input_channel, encoder_output_channels[i], 1, nlin_layer=nn.LeakyReLU))
            encoder.append(conv_block(encoder_output_channels[i], encoder_output_channels[i],1,nlin_layer=nn.LeakyReLU))
            encoder.append(nn.MaxPool2d(2,2))
            if(i != layer_num-1):
                encoder.append(nn.Dropout2d(p=0.3))
            input_channel = encoder_output_channels[i]

        #make decoder
        for i in range(layer_num):
            decoder.append(nn.Upsample(scale_factor=2))
            decoder.append(conv_block(input_channel, input_channel, 1, nlin_layer=nn.LeakyReLU))
            decoder.append(conv_block(input_channel, decoder_output_channels[i], 1, nlin_layer=nn.LeakyReLU))
            if(i != layer_num-1):
                decoder.append(nn.Dropout2d(p=0.3))
            input_channel = decoder_output_channels[i]


        encoder = nn.Sequential(*encoder)
        decoder = nn.Sequential(*decoder)
        return encoder, decoder

    def forward(self, x):
        x = self.encoder(x)
        print(x.shape)
        x = self.decoder(x)
        return x


class pytorch_autoencoder(nn.Module):
    def __init__(self):
        super(pytorch_autoencoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Conv2d(1, 32, 2, stride=2, padding=0),  
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=2),
            nn.Conv2d(32, 16, 2, stride=2, padding=0),
            nn.ReLU(True),
        )
        self.decoder = nn.Sequential(
            nn.ConvTranspose2d(16, 32, 2, stride=2),  
            nn.ReLU(True),
            nn.ConvTranspose2d(32, 64, 2, stride=2, padding=0),  
            nn.ReLU(True),
            nn.ConvTranspose2d(64, 1, 2, stride=2, padding=0),
            nn.Tanh()
        )

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x