# Copyright (c) Soumith Chintala 2016,
# All rights reserved
#
# Copyright 2020 Huawei Technologies Co., Ltd
#
# Licensed under the BSD 3-Clause License (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://spdx.org/licenses/BSD-3-Clause.html
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

#resnet implement : https://github.com/pytorch/vision/tree/master/torchvision

import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo

__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, 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))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        self.C1_down_channel = nn.Conv2d(64, 21, 1)
        self.C2_down_channel = nn.Conv2d(256, 21, 1)
        self.C3_down_channel = nn.Conv2d(512, 21, 1)
        self.C4_down_channel = nn.Conv2d(1024, 21, 1)
        self.C5_down_channel = nn.Conv2d(2048, 21, 1)

        self.score_dsn1 = nn.Conv2d(21, 1, 1)
        self.score_dsn2 = nn.Conv2d(21, 1, 1)
        self.score_dsn3 = nn.Conv2d(21, 1, 1)
        self.score_dsn4 = nn.Conv2d(21, 1, 1)
        self.score_dsn5 = nn.Conv2d(21, 1, 1)
        self.score_final = nn.Conv2d(5, 1, 1)


        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, size):
        #x 1
#        print("def forward(self, x, size):")
#        print("x:",x.shape, x.dtype)
        x = self.conv1(x)  #1/2
        x = self.bn1(x)
        x = self.relu(x)
        C1 = self.maxpool(x) #1/4
        C2 = self.layer1(C1) #1/4
        C3 = self.layer2(C2) #1/8
        C4 = self.layer3(C3) #1/16
        C5 = self.layer4(C4) #1/32


        R1 = self.relu(self.C1_down_channel(C1))
        R2 = self.relu(self.C2_down_channel(C2))
        R3 = self.relu(self.C3_down_channel(C3))
        R4 = self.relu(self.C4_down_channel(C4))
        R5 = self.relu(self.C5_down_channel(C5))

        so1_out = self.score_dsn1(R1)
        so2_out = self.score_dsn2(R2)
        so3_out = self.score_dsn3(R3)
        so4_out = self.score_dsn4(R4)
        so5_out = self.score_dsn4(R5)

        upsample = nn.UpsamplingBilinear2d(size)


        out1 = upsample(so1_out)
        out2 = upsample(so2_out)
        out3 = upsample(so3_out)
        out4 = upsample(so4_out)
#        out4 = upsample.cpu()(so4_out.cpu())
#        out4 = out4.npu()
        out5 = upsample(so5_out)
#        out5 = upsample.cpu()(so5_out.cpu())
#        out5 = out5.npu()

        # out3 = nn.UpsamplingBilinear2d(so3_out, size)
        # out4 = nn.UpsamplingBilinear2d(so4_out, size)
        # out5 = nn.UpsamplingBilinear2d(so5_out, size)

        # print('C3 and R3', C3.size(), R3.size())
        # print('C5 and R5', C5.size(), R5.size())
        # print('s o out 1 3 5', so1_out.size(), so3_out.size(), so5_out.size())
        # print(out1)
        # print(out1.size(), out2.size(), out3.size(), out4.size(), out5.size())

        fuse = torch.cat([out1, out2, out3, out4, out5], dim=1)
        final_out = self.score_final(fuse)
        # print('fuse ', fuse.size())
        # print('final out', final_out.size())

        results = [out1, out2, out3, out4, out5, final_out]
        results = [torch.sigmoid(r) for r in results]
        return results

        # fully-connected layer is not needed.
        # x = self.avgpool(x)
        # print('x .. 7', x.size())
        # x = x.view(x.size(0), -1)
        # x = self.fc(x)
        # return x



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']))
    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']), strict=False)
    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