import os
import sys
import torch
import torch.nn as nn
import math
try:
    from lib.nn import SynchronizedBatchNorm2d
except ImportError:
    from torch.nn import BatchNorm2d as SynchronizedBatchNorm2d

try:
    from urllib import urlretrieve
except ImportError:
    from urllib.request import urlretrieve


__all__ = ['ResNeXt', 'resnext101'] # support resnext 101


model_urls = {
    #'resnext50': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnext50-imagenet.pth',
    'resnext101': 'http://sceneparsing.csail.mit.edu/model/pretrained_resnet/resnext101-imagenet.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)


class GroupBottleneck(nn.Module):
    expansion = 2

    def __init__(self, inplanes, planes, stride=1, groups=1, downsample=None):
        super(GroupBottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = SynchronizedBatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, groups=groups, bias=False)
        self.bn2 = SynchronizedBatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 2, kernel_size=1, bias=False)
        self.bn3 = SynchronizedBatchNorm2d(planes * 2)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = 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:
            residual = self.downsample(x)

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

        return out


class ResNeXt(nn.Module):

    def __init__(self, block, layers, groups=32, num_classes=1000):
        self.inplanes = 128
        super(ResNeXt, self).__init__()
        self.conv1 = conv3x3(3, 64, stride=2)
        self.bn1 = SynchronizedBatchNorm2d(64)
        self.relu1 = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(64, 64)
        self.bn2 = SynchronizedBatchNorm2d(64)
        self.relu2 = nn.ReLU(inplace=True)
        self.conv3 = conv3x3(64, 128)
        self.bn3 = SynchronizedBatchNorm2d(128)
        self.relu3 = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self._make_layer(block, 128, layers[0], groups=groups)
        self.layer2 = self._make_layer(block, 256, layers[1], stride=2, groups=groups)
        self.layer3 = self._make_layer(block, 512, layers[2], stride=2, groups=groups)
        self.layer4 = self._make_layer(block, 1024, layers[3], stride=2, groups=groups)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(1024 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels // m.groups
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, SynchronizedBatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1, groups=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                SynchronizedBatchNorm2d(planes * block.expansion),
            )

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

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.relu1(self.bn1(self.conv1(x)))
        x = self.relu2(self.bn2(self.conv2(x)))
        x = self.relu3(self.bn3(self.conv3(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.view(x.size(0), -1)
        x = self.fc(x)

        return x


'''
def resnext50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on Places
    """
    model = ResNeXt(GroupBottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(load_url(model_urls['resnext50']), strict=False)
    return model
'''


def resnext101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on Places
    """
    model = ResNeXt(GroupBottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        model.load_state_dict(load_url(model_urls['resnext101']), strict=False)
    return model


# def resnext152(pretrained=False, **kwargs):
#     """Constructs a ResNeXt-152 model.
#
#     Args:
#         pretrained (bool): If True, returns a model pre-trained on Places
#     """
#     model = ResNeXt(GroupBottleneck, [3, 8, 36, 3], **kwargs)
#     if pretrained:
#         model.load_state_dict(load_url(model_urls['resnext152']))
#     return model


def load_url(url, model_dir='./pretrained', map_location=None):
    if not os.path.exists(model_dir):
        os.makedirs(model_dir)
    filename = url.split('/')[-1]
    cached_file = os.path.join(model_dir, filename)
    if not os.path.exists(cached_file):
        sys.stderr.write('Downloading: "{}" to {}\n'.format(url, cached_file))
        urlretrieve(url, cached_file)
    return torch.load(cached_file, map_location=map_location)