import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import torch
import os
import numpy as np
import cv2
from utils import landmark_processor, utils_3ddfa, params_3ddfa

__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']


model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, 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 BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(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

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = conv1x1(inplanes, planes)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = conv1x1(planes, planes * self.expansion)
        self.bn3 = nn.BatchNorm2d(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, num_classes=1000, no_branch=False, no_activate=False, zero_init_residual=False):
        super(ResNet, self).__init__()
        self.inplanes = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        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)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        if no_activate:
            if no_branch:
                self.fc = nn.Sequential(*[nn.Linear(512 * block.expansion, num_classes)])
            else:
                self.fc_key = nn.Sequential(*[nn.Linear(256 * block.expansion, 45 * 2)])
                self.fc_ctrl = nn.Sequential(*[nn.Linear(256 * block.expansion, 48 * 2)])
        else:
            if no_branch:
                self.fc = nn.Sequential(*[nn.Linear(512 * block.expansion, num_classes), nn.Tanh()])
            else:
                self.fc_key = nn.Sequential(*[nn.Linear(256 * block.expansion, 45 * 2), nn.Tanh()])
                self.fc_ctrl = nn.Sequential(*[nn.Linear(256 * block.expansion, 48 * 2), nn.Tanh()])
        self.no_branch = no_branch

        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.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):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                nn.BatchNorm2d(planes * block.expansion),
            )

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

        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)

        if self.no_branch:
            key = self.avgpool(x)
            key = key.view(-1, 512)
            key = self.fc(key)
            return key
        else:
            key, ctrl = torch.chunk(x, 2, dim=1)

            key = self.avgpool(key)
            key = key.view(key.size(0), -1)
            key = self.fc_key(key)

            ctrl = self.avgpool(ctrl)
            ctrl = ctrl.view(ctrl.size(0), -1)
            ctrl = self.fc_ctrl(ctrl)

            return key, ctrl

def resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)
    return model


def resnet34(pretrained=False, **kwargs):
    """Constructs a ResNet-34 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
    return model


def resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
    return model


def resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
    return model


def resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
    return model


class Model_3DDFA(nn.Module):
    def __init__(self, gpu_id=None):
        super(Model_3DDFA, self).__init__()

        self.face_alignment_net = resnet18(pretrained=False, num_classes=76, no_branch=True, no_activate=True)

        model_path, _ = os.path.split(os.path.realpath(__file__))
        weights = torch.load(os.path.join(model_path, 'face_3ddfa.pth'), map_location=lambda storage, loc: storage)
        self.load_state_dict(weights)
        self.eval()
        self.device = torch.device('cuda:{}'.format(gpu_id) if gpu_id is not None else 'cpu')
        self.to(self.device)

    def forward(self, imgs):
        pred_pose_shape_exp = self.face_alignment_net(imgs)
        return pred_pose_shape_exp

    def forward_np(self, imgs):
        pred_pose_shape_exp = self.face_alignment_net(imgs)
        return pred_pose_shape_exp.detach().cpu().numpy()

    def detect(self, images, landmarks):
        dst_size = 256
        with torch.no_grad():
            input_numpy = np.zeros((len(images), 3, dst_size, dst_size), dtype=np.float32)
            assert len(images) == len(landmarks)
            all_mat = []
            all_res = []
            all_height = []
            for ix, img in enumerate(images):
                landmark = landmarks[ix]

                mat = landmark_processor.get_transform_mat_full_face(landmark, dst_size)

                all_mat.append(mat)
                all_height.append(img.shape[0])

                tmp = cv2.warpAffine(img, mat, (dst_size, dst_size))

                input_numpy[ix, :, :, :] = tmp.transpose((2, 0, 1)).astype(np.float32) / 255

                # cv2.imshow('3ddfa_', tmp)
                # cv2.waitKey()

            in_tensor = torch.from_numpy(input_numpy)
            in_tensor = in_tensor.to(self.device)
            params = self.face_alignment_net(in_tensor)
            params = params.cpu().numpy()

            for ix, param in enumerate(params):
                param[0] = param[0] / params_3ddfa.SCALE_F
                param[1:4] = param[1:4] / params_3ddfa.SCALE_ROTATE
                param[4:6] = param[4:6] / params_3ddfa.SCALE_OFFSET
                param[6:56] = (param[6:56] / params_3ddfa.SCALE_SHAPE)
                param[56:] = (param[56:] / params_3ddfa.SCALE_EXP)
                new_param = utils_3ddfa.transform_params(param, cv2.invertAffineTransform(all_mat[ix]), all_height[ix], dst_size)
                all_res.append(new_param)

            return all_res