import torch
import torch.nn as nn
import os


__all__ = [
    "ResNet",
    "resnet18_with_dropout",
    "resnet18",
    "dropout_resnet18"
]


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

    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 BasicBlock_withDropout(nn.Module):
    expansion = 1

    def __init__(
        self,
        inplanes,
        planes,
        stride=1,
        downsample=None,
        groups=1,
        base_width=64,
        dilation=1,
        norm_layer=None,
    ):
        super(BasicBlock_withDropout, 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.dropout = nn.Dropout(p=0.5)
        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
        # print('with_dropout',self.with_dropout)

    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

    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 / 64.0)) * 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


class ResNet(nn.Module):
    def __init__(
        self,
        block,
        layers,
        with_dropout,
        num_classes=10,
        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.with_dropout = with_dropout
        self.groups = groups
        self.base_width = width_per_group

        # CIFAR10: kernel_size 7 -> 3, stride 2 -> 1, padding 3->1
        self.conv1 = nn.Conv2d(
            3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False
        )
        # END

        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)

        if self.with_dropout:
            self.fc = nn.Sequential(nn.Flatten(),nn.Dropout(0.5),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(self, x):
        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 = x.reshape(x.size(0), -1)
        x = self.fc(x)

        return x
    
    def feature(self, x):
        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 = x.reshape(x.size(0), -1)
        return x
    def prediction(self,x):
        x = self.fc(x)

        return x

    # def gap(self, x):
    #     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 = x.reshape(x.size(0), -1)
    #     return x


def _resnet(arch, block, layers, pretrained, progress, device, with_dropout, **kwargs):
    model = ResNet(block, layers, with_dropout, **kwargs)
    if pretrained:
        script_dir = os.path.dirname(__file__)
        state_dict = torch.load(
            script_dir + "/state_dicts/" + arch + ".pt", map_location=device
        )
        model.load_state_dict(state_dict)
    return model


def resnet18_with_dropout(pretrained=False, progress=True, device="cpu", **kwargs):
    """Constructs a ResNet-18 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _resnet(
        "resnet18", BasicBlock_withDropout, [2, 2, 2, 2], pretrained, progress, device, with_dropout = True, **kwargs
    )

def resnet18(pretrained=False, progress=True, device="cpu", **kwargs):
    """Constructs a ResNet-18 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _resnet(
        "resnet18", BasicBlock, [2, 2, 2, 2], pretrained, progress, device, with_dropout = False, **kwargs
    )


def resnet34(pretrained=False, progress=True, device="cpu", **kwargs):
    """Constructs a ResNet-34 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _resnet(
        "resnet34", BasicBlock, [3, 4, 6, 3], pretrained, progress, device, **kwargs
    )


def resnet50(pretrained=False, progress=True, device="cpu", **kwargs):
    """Constructs a ResNet-50 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _resnet(
        "resnet50", Bottleneck, [3, 4, 6, 3], pretrained, progress, device, **kwargs
    )

# class dropout_residual(nn.Module):
#   def __init__(self, input_channels, num_channels, dropout_rate, dropout_type, init_dict, use_1x1conv=False, strides=1, **kwargs):
#     super().__init__(**kwargs)
#     self.conv1 = Dropout_Conv2D(input_channels, num_channels, kernel_size=3, padding=1, stride=strides, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict)
#     self.conv2 = Dropout_Conv2D(num_channels, num_channels, kernel_size=3, padding=1, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict)

#     if use_1x1conv:
#       self.conv3 = Dropout_Conv2D(input_channels, num_channels, kernel_size=1, stride=strides, dropout_rate=dropout_rate, dropout_type=dropout_type)
#     else:
#       self.conv3 = None
    
#     self.bn1 = nn.BatchNorm2d(num_channels)
#     self.bn2 = nn.BatchNorm2d(num_channels)

# def dropout_resnet_block(input_channels, num_channels, num_residuals, dropout_rate, dropout_type, init_dict, first_block=False):
#   blk = []
#   for i in range(num_residuals):
#     if i == 0 and not first_block:
#       blk.append(dropout_residual(input_channels, num_channels, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict, use_1x1conv=True, strides=2))
#     else:
#       blk.append(dropout_residual(num_channels, num_channels, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict))
#   return blk

# def dropout_resnet18(dropout_rate=0.5, dropout_type="w", init_dict=dict()):
#   b1 = nn.Sequential(
#       Dropout_Conv2D(1, 64, kernel_size=7, stride=2, padding=3, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict),
#       nn.BatchNorm2d(64),
#       nn.ReLU(),
#       nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
#     )
#   b2 = nn.Sequential(*dropout_resnet_block(64, 64, 2, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict, first_block=True))
#   b3 = nn.Sequential(*dropout_resnet_block(64, 128, 2, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict))
#   b4 = nn.Sequential(*dropout_resnet_block(128, 256, 2, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict))
#   b5 = nn.Sequential(*dropout_resnet_block(256, 512, 2, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict))

#   return nn.Sequential(b1, b2, b3, b4, b5,
#                        nn.AdaptiveAvgPool2d((1,1)),
#                        nn.Flatten(),
#                        Dropout_Linear(512, 20, dropout_rate=dropout_rate, dropout_type=dropout_type, init_dict=init_dict))