import torch
from torch import nn
from torch.utils.checkpoint import checkpoint

using_ckpt = False


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


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 IBasicBlock(nn.Module):
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(IBasicBlock, self).__init__()
        self.bn1 = nn.BatchNorm2d(inplanes, eps=1e-05,)
        self.conv1 = conv3x3(inplanes, planes)
        self.bn2 = nn.BatchNorm2d(planes, eps=1e-05,)
        self.prelu = nn.PReLU(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn3 = nn.BatchNorm2d(planes, eps=1e-05,)
        self.downsample = downsample
        self.stride = stride

    def forward_impl(self, x):
        identity = x
        out = self.bn1(x)
        out = self.conv1(out)
        out = self.bn2(out)
        out = self.prelu(out)
        out = self.conv2(out)
        out = self.bn3(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        return out

    def forward(self, x):
        if self.training and using_ckpt:
            return checkpoint(self.forward_impl, x)
        else:
            return self.forward_impl(x)


class IResNet(nn.Module):
    def __init__(self,
                 block, layers, dropout=0.4, num_features=512, zero_init_residual=False,
                 groups=1, fp16=False):
        super(IResNet, self).__init__()
        self.extra_gflops = 0.0
        self.fp16 = fp16
        self.inplanes = 64

        self.groups = groups
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(self.inplanes, eps=1e-05)
        self.prelu = nn.PReLU(self.inplanes)
        self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
        self.layer2 = self._make_layer(block,
                                       128,
                                       layers[1],
                                       stride=2)
        self.layer3 = self._make_layer(block,
                                       256,
                                       layers[2],
                                       stride=2)
        self.layer4 = self._make_layer(block,
                                       512,
                                       layers[3],
                                       stride=2)
        self.bn2 = nn.BatchNorm2d(512, eps=1e-05,)
        self.dropout = nn.Dropout(p=dropout, inplace=True)
        self.fc = nn.Linear(512 * 7 * 7, num_features)
        self.features = nn.BatchNorm1d(num_features, eps=1e-05)
        nn.init.constant_(self.features.weight, 1.0)
        self.features.weight.requires_grad = False

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight, 0, 0.1)
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, IBasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes, stride),
                nn.BatchNorm2d(planes, eps=1e-05, ),
            )
        layers = []
        layers.append(
            block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes
        for _ in range(1, blocks):
            layers.append(
                block(self.inplanes,
                      planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        with torch.cuda.amp.autocast(self.fp16):
            x = self.conv1(x)
            x = self.bn1(x)
            x = self.prelu(x)
            x = self.layer1(x)
            x = self.layer2(x)
            x = self.layer3(x)
            x = self.layer4(x)
            x = self.bn2(x)
            x = torch.flatten(x, 1)
            x = self.dropout(x)
        x = self.fc(x.float() if self.fp16 else x)
        x = self.features(x)
        return x


def iresnet(arch, pretrained=False, **kwargs):
    layer_dict = {"18": [2, 2, 2, 2],
                  "34": [3, 4, 6, 3],
                  "50": [3, 4, 14, 3],
                  "100": [3, 13, 30, 3],
                  "152": [3, 8, 36, 3],
                  "200": [3, 13, 30, 3]}
    model = IResNet(IBasicBlock, layer_dict[arch], **kwargs)
    if pretrained:
        raise ValueError()
    return model