import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import models
from torchvision.models.vgg import VGG

import torch
import torch.nn as nn
#from .utils import load_state_dict_from_url


__all__ = [
    'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
    'vgg19_bn', 'vgg19',
]


model_urls = {
    'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
    'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
    'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
    'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
    'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
    'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}


class VGG(nn.Module):

    def __init__(self, features, num_classes=1000, init_weights=True):
        super(VGG, self).__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)


def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


cfgs = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def _vgg(arch, cfg, batch_norm, pretrained, progress, **kwargs):
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs)
    if pretrained:
        state_dict = load_state_dict_from_url(model_urls[arch],
                                              progress=progress)
        model.load_state_dict(state_dict)
    return model


def vgg11(pretrained=False, progress=True, **kwargs):
    r"""VGG 11-layer model (configuration "A") from
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg11', 'A', False, pretrained, progress, **kwargs)


def vgg11_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 11-layer model (configuration "A") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg11_bn', 'A', True, pretrained, progress, **kwargs)


def vgg13(pretrained=False, progress=True, **kwargs):
    r"""VGG 13-layer model (configuration "B")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg13', 'B', False, pretrained, progress, **kwargs)


def vgg13_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 13-layer model (configuration "B") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg13_bn', 'B', True, pretrained, progress, **kwargs)


def vgg16(pretrained=False, progress=True, **kwargs):
    r"""VGG 16-layer model (configuration "D")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)


def vgg16_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 16-layer model (configuration "D") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg16_bn', 'D', True, pretrained, progress, **kwargs)


def vgg19(pretrained=False, progress=True, **kwargs):
    r"""VGG 19-layer model (configuration "E")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg19', 'E', False, pretrained, progress, **kwargs)


def vgg19_bn(pretrained=False, progress=True, **kwargs):
    r"""VGG 19-layer model (configuration 'E') with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    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 _vgg('vgg19_bn', 'E', True, pretrained, progress, **kwargs)


class FCN32s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(64, n_class, kernel_size=1)
        self.sigmoid = nn.Sigmoid()
    def forward(self, x):
        #print(x.shape)
        output = self.pretrained_net(x)
        # print(output['x1'].shape)
        # print(output['x2'].shape)
        # print(output['x3'].shape)
        # print(output['x4'].shape)
        x4 = output['x4']  # size=(N, 512, x.H/32, x.W/32)
        #print(x5.shape)
        score = self.bn1(self.relu(self.deconv1(x4)))     # size=(N, 512, x.H/16, x.W/16)
        #print(score.shape)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        #print(score.shape)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        #print(score.shape)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        #print(score.shape)
        #score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)
        score = self.sigmoid(score)
        # print(score.shape)
        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCN16s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)

        score = self.relu(self.deconv1(x5))               # size=(N, 512, x.H/16, x.W/16)
        score = self.bn1(score + x4)                      # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCN8s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)
        x3 = output['x3']  # size=(N, 256, x.H/8,  x.W/8)

        score = self.relu(self.deconv1(x5))               # size=(N, 512, x.H/16, x.W/16)
        score = self.bn1(score + x4)                      # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.relu(self.deconv2(score))            # size=(N, 256, x.H/8, x.W/8)
        score = self.bn2(score + x3)                      # element-wise add, size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)
        score = nn.Sigmoid()(score)
        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCNs(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)
        x3 = output['x3']  # size=(N, 256, x.H/8,  x.W/8)
        x2 = output['x2']  # size=(N, 128, x.H/4,  x.W/4)
        x1 = output['x1']  # size=(N, 64, x.H/2,  x.W/2)

        score = self.bn1(self.relu(self.deconv1(x5)))     # size=(N, 512, x.H/16, x.W/16)
        score = score + x4                                # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        score = score + x3                                # element-wise add, size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = score + x2                                # element-wise add, size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = score + x1                                # element-wise add, size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class VGGNet(VGG):
    def __init__(self, pretrained=True, model='vgg16', requires_grad=True, remove_fc=True, show_params=False):
        super().__init__(make_layers(cfg[model]))
        self.ranges = ranges[model]

        if pretrained:
            exec("self.load_state_dict(models.%s(pretrained=True).state_dict())" % model)

        if not requires_grad:
            for param in super().parameters():
                param.requires_grad = False

        if remove_fc:  # delete redundant fully-connected layer params, can save memory
            del self.classifier

        if show_params:
            for name, param in self.named_parameters():
                print(name, param.size())

    def forward(self, x):
        output = {}

        # get the output of each maxpooling layer (5 maxpool in VGG net)
        for idx in range(len(self.ranges)):
            for layer in range(self.ranges[idx][0], self.ranges[idx][1]):
                x = self.features[layer](x)
            output["x%d"%(idx+1)] = x

        return output


ranges = {
    'vgg11': ((0, 3), (3, 6),  (6, 11),  (11, 16), (16, 21)),
    'vgg13': ((0, 5), (5, 10), (10, 15), (15, 20), (20, 25)),
    'vgg16': ((0, 5), (5, 10), (10, 17), (17, 24), (24, 31)),
    'vgg19': ((0, 5), (5, 10), (10, 19), (19, 28), (28, 37))
}

# cropped version from https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
cfg = {
    'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}

def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)

def get_fcn32s(n_class=1):
    vgg_model = VGGNet(requires_grad=True)
    return FCN32s(pretrained_net=vgg_model, n_class=n_class)
def get_fcn8s(n_class=1):
    vgg_model = VGGNet(requires_grad=True)
    return FCN8s(pretrained_net=vgg_model, n_class=n_class)