import math
import torch
import torch.nn as nn
import torch.nn.functional as F


import higher
class Higher_model(nn.Module):
    def __init__(self, model):
        super(Higher_model, self).__init__()

        self._mods = nn.ModuleDict({
            'original': model,
            'functional': higher.patch.monkeypatch(model, device=None, copy_initial_weights=True)
            })

    def get_diffopt(self, opt, grad_callback=None, track_higher_grads=True):
        return higher.optim.get_diff_optim(opt, 
            self._mods['original'].parameters(),
            fmodel=self._mods['functional'],
            grad_callback=grad_callback,
            track_higher_grads=track_higher_grads)

    def forward(self, x):
        return self._mods['functional'](x)

    def detach_(self):
        tmp = self._mods['functional'].fast_params
        self._mods['functional']._fast_params=[]
        self._mods['functional'].update_params(tmp)
        for p in self._mods['functional'].fast_params:
            p.detach_().requires_grad_()

    def __getitem__(self, key):
        return self._mods[key]

    def __str__(self):
        return self._mods['original'].__str__()

## Basic CNN ##
class LeNet_F(nn.Module):
    def __init__(self, num_inp, num_out):
        super(LeNet_F, self).__init__()
        self._params = nn.ParameterDict({
            'w1': nn.Parameter(torch.zeros(20, num_inp, 5, 5)),
            'b1': nn.Parameter(torch.zeros(20)),
            'w2': nn.Parameter(torch.zeros(50, 20, 5, 5)),
            'b2': nn.Parameter(torch.zeros(50)),
            #'w3': nn.Parameter(torch.zeros(500,4*4*50)), #num_imp=1
            'w3': nn.Parameter(torch.zeros(500,5*5*50)), #num_imp=3
            'b3': nn.Parameter(torch.zeros(500)),
            'w4': nn.Parameter(torch.zeros(num_out, 500)),
            'b4': nn.Parameter(torch.zeros(num_out))
        })
        self.initialize()


    def initialize(self):
        nn.init.kaiming_uniform_(self._params["w1"], a=math.sqrt(5))
        nn.init.kaiming_uniform_(self._params["w2"], a=math.sqrt(5))
        nn.init.kaiming_uniform_(self._params["w3"], a=math.sqrt(5))
        nn.init.kaiming_uniform_(self._params["w4"], a=math.sqrt(5))

    def forward(self, x):
        #print("Start Shape ", x.shape)
        out = F.relu(F.conv2d(input=x, weight=self._params["w1"], bias=self._params["b1"]))
        #print("Shape ", out.shape)
        out = F.max_pool2d(out, 2)
        #print("Shape ", out.shape)
        out = F.relu(F.conv2d(input=out, weight=self._params["w2"], bias=self._params["b2"]))
        #print("Shape ", out.shape)
        out = F.max_pool2d(out, 2)
        #print("Shape ", out.shape)
        out = out.view(out.size(0), -1)
        #print("Shape ", out.shape)
        out = F.relu(F.linear(out, self._params["w3"], self._params["b3"]))
        #print("Shape ", out.shape)
        out = F.linear(out, self._params["w4"], self._params["b4"])
        #print("Shape ", out.shape)
        #return F.log_softmax(out, dim=1)
        return out

    def __getitem__(self, key):
        return self._params[key]

    def __str__(self):
        return "LeNet"

class LeNet(nn.Module):
    def __init__(self, num_inp, num_out):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(num_inp, 20, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(20, 50, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(5*5*50, 500)
        self.fc2 = nn.Linear(500, num_out)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

    def __str__(self):
        return "LeNet"

## MobileNetv2 ##

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,
                 num_classes=1000,
                 width_mult=1.0,
                 inverted_residual_setting=None,
                 round_nearest=8,
                 block=None):
        """
        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__()

        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)

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

        # 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])
        x = self.classifier(x)
        return x

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

    def __str__(self):
        return "MobileNetV2"

## ResNet ##
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation)


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
    expansion = 1
    __constants__ = ['downsample']

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4
    __constants__ = ['downsample']

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out

#ResNet18 : block=BasicBlock, layers=[2, 2, 2, 2]
class ResNet(nn.Module):

    def __init__(self, block=BasicBlock, layers=[2, 2, 2, 2], num_classes=1000, zero_init_residual=False,
                 groups=1, width_per_group=64, replace_stride_with_dilation=None,
                 norm_layer=None):
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer

        self.inplanes = 64
        self.dilation = 1
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError("replace_stride_with_dilation should be None "
                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
        self.groups = groups
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = norm_layer(self.inplanes)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
                                       dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
                                       dilate=replace_stride_with_dilation[1])
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
                                       dilate=replace_stride_with_dilation[2])
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        # Zero-initialize the last BN in each residual branch,
        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
                            self.base_width, previous_dilation, norm_layer))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes, groups=self.groups,
                                base_width=self.base_width, dilation=self.dilation,
                                norm_layer=norm_layer))

        return nn.Sequential(*layers)

    def _forward_impl(self, x):
        # See note [TorchScript super()]
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x

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

    def __str__(self):
        return "ResNet18"

## Wide ResNet ##
#https://github.com/xternalz/WideResNet-pytorch/blob/master/wideresnet.py
#https://github.com/arcelien/pba/blob/master/pba/wrn.py
#https://github.com/szagoruyko/wide-residual-networks/blob/master/pytorch/resnet.py
'''
class BasicBlock(nn.Module):
    def __init__(self, in_planes, out_planes, stride, dropRate=0.0):
        super(BasicBlock, self).__init__()
        self.bn1 = nn.BatchNorm2d(in_planes)
        self.relu1 = nn.ReLU(inplace=True)
        self.conv1 = nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_planes)
        self.relu2 = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_planes, out_planes, kernel_size=3, stride=1,
                               padding=1, bias=False)
        self.droprate = dropRate
        self.equalInOut = (in_planes == out_planes)
        self.convShortcut = (not self.equalInOut) and nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride,
                               padding=0, bias=False) or None
    def forward(self, x):
        if not self.equalInOut:
            x = self.relu1(self.bn1(x))
        else:
            out = self.relu1(self.bn1(x))
        out = self.relu2(self.bn2(self.conv1(out if self.equalInOut else x)))
        if self.droprate > 0:
            out = F.dropout(out, p=self.droprate, training=self.training)
        out = self.conv2(out)
        return torch.add(x if self.equalInOut else self.convShortcut(x), out)

class NetworkBlock(nn.Module):
    def __init__(self, nb_layers, in_planes, out_planes, block, stride, dropRate=0.0):
        super(NetworkBlock, self).__init__()
        self.layer = self._make_layer(block, in_planes, out_planes, nb_layers, stride, dropRate)
    def _make_layer(self, block, in_planes, out_planes, nb_layers, stride, dropRate):
        layers = []
        for i in range(int(nb_layers)):
            layers.append(block(i == 0 and in_planes or out_planes, out_planes, i == 0 and stride or 1, dropRate))
        return nn.Sequential(*layers)
    def forward(self, x):
        return self.layer(x)

#wrn_size: 32 = WRN-28-2 ? 160 = WRN-28-10
class WideResNet(nn.Module):
    #def __init__(self, depth, num_classes, widen_factor=1, dropRate=0.0):
    def __init__(self, num_classes, wrn_size, depth=28, dropRate=0.0):
        super(WideResNet, self).__init__()

        self.kernel_size = wrn_size
        self.depth=depth
        filter_size = 3
        nChannels = [min(self.kernel_size, 16), self.kernel_size, self.kernel_size * 2, self.kernel_size * 4]
        strides = [1, 2, 2]  # stride for each resblock

        #nChannels = [16, 16*widen_factor, 32*widen_factor, 64*widen_factor]
        assert((depth - 4) % 6 == 0)
        n = (depth - 4) / 6
        block = BasicBlock
        # 1st conv before any network block
        self.conv1 = nn.Conv2d(filter_size, nChannels[0], kernel_size=3, stride=1,
                               padding=1, bias=False)
        # 1st block
        self.block1 = NetworkBlock(n, nChannels[0], nChannels[1], block, strides[0], dropRate)
        # 2nd block
        self.block2 = NetworkBlock(n, nChannels[1], nChannels[2], block, strides[1], dropRate)
        # 3rd block
        self.block3 = NetworkBlock(n, nChannels[2], nChannels[3], block, strides[2], dropRate)
        # global average pooling and classifier
        self.bn1 = nn.BatchNorm2d(nChannels[3])
        self.relu = nn.ReLU(inplace=True)
        self.fc = nn.Linear(nChannels[3], num_classes)
        self.nChannels = nChannels[3]

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.bias.data.zero_()
    def forward(self, x):
        out = self.conv1(x)
        out = self.block1(out)
        out = self.block2(out)
        out = self.block3(out)
        out = self.relu(self.bn1(out))
        out = F.avg_pool2d(out, 8)
        out = out.view(-1, self.nChannels)
        return self.fc(out)

    def architecture(self):
        return super(WideResNet, self).__str__()

    def __str__(self):
        return "WideResNet(s{}-d{})".format(self.kernel_size, self.depth)
'''