# Copyright (c) Facebook, Inc. and its affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
#

import torch
import torch.nn as nn


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


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
    __constants__ = ["downsample"]

    def __init__(
        self,
        inplanes,
        planes,
        stride=1,
        downsample=None,
        groups=1,
        base_width=64,
        dilation=1,
        norm_layer=None,
    ):
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError("BasicBlock only supports groups=1 and base_width=64")
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(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
    __constants__ = ["downsample"]

    def __init__(
        self,
        inplanes,
        planes,
        stride=1,
        downsample=None,
        groups=1,
        base_width=64,
        dilation=1,
        norm_layer=None,
    ):
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.0)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(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,
            groups=1,
            widen=1,
            width_per_group=64,
            replace_stride_with_dilation=None,
            norm_layer=None,
    ):
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer

        self.inplanes = width_per_group * widen
        self.dilation = 1
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError(
                "replace_stride_with_dilation should be None "
                "or a 3-element tuple, got {}".format(replace_stride_with_dilation)
            )
        self.groups = groups
        self.base_width = width_per_group

        num_out_filters = width_per_group * widen
        self.conv1 = nn.Conv2d(
            3, num_out_filters, kernel_size=7, stride=2, padding=3, bias=False
        )
        self.bn1 = norm_layer(num_out_filters)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, num_out_filters, layers[0])
        num_out_filters *= 2
        self.layer2 = self._make_layer(
            block, num_out_filters, layers[1], stride=2, dilate=replace_stride_with_dilation[0]
        )
        #num_out_filters *= 2
        #self.layer3 = self._make_layer(
        #    block, num_out_filters, layers[2], stride=2, dilate=replace_stride_with_dilation[1]
        #)
        #num_out_filters *= 2
        #self.layer4 = self._make_layer(
        #    block, num_out_filters, layers[3], stride=2, dilate=replace_stride_with_dilation[2]
        #)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        #self.fc = nn.Linear(512 * block.expansion * widen, num_classes)

        # 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, dilate=False):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )

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

        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)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        #x = self.fc(x)

        return x


def resnet50(**kwargs):
    return ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)


def resnet50w2(**kwargs):
    return ResNet(Bottleneck, [3, 4, 6, 3], widen=2, **kwargs)


def resnet50w4(**kwargs):
    return ResNet(Bottleneck, [3, 4, 6, 3], widen=4, **kwargs)


def resnet50w5(**kwargs):
    return ResNet(Bottleneck, [3, 4, 6, 3], widen=5, **kwargs)


if __name__ == '__main__':
    import onnxruntime as ort
    x=torch.rand(1,3,224,224)
    model = resnet50w2()
    model.eval()

    swav_state_dict = torch.load('/opt/software/github/he-ai/swav_RN50w2_400ep_pretrain.pth.tar')

    for k in list(swav_state_dict.keys()):
        if k.startswith('module.layer3') or k.startswith('module.layer4') or k.startswith('module.pro'):del swav_state_dict[k]

    for k in list(swav_state_dict.keys()):
        swav_state_dict[k.replace('module.', '')] = swav_state_dict[k]
        del swav_state_dict[k]
    msg = model.load_state_dict(swav_state_dict, strict=False)
    print(msg)
    torch.save(swav_state_dict, 'swav_imagenet_layer2.pt')

    traced_script_module = torch.jit.trace(model, x)
    traced_script_module.save("traced_swav_imagenet_layer2.pt")
    traced_feature = traced_script_module(x).detach().cpu().numpy()
    print(traced_feature)
    print(model(x))


    dynamic_axes={"x": {0:"batch_size"}, 'feature': {0:'batch_size'}}
    torch.onnx.export(model, x, "swav_imagenet_layer2.onnx", verbose=False, input_names=['x'], output_names=['feature'], dynamic_axes=dynamic_axes, do_constant_folding=True)
    ort_session = ort.InferenceSession("swav_imagenet_layer2.onnx")
    onnx_outputs = ort_session.run(None, {'x':x.numpy()})
    print(onnx_outputs[0])