functions/tres_functions.py

"""
Source: https://github.com/isalirezag/TReS/
"""

import torch
import torchvision.models as models
import torchvision
import torch.nn.functional as F
from torch import nn, Tensor

import numpy as np
from scipy import stats
from tqdm import tqdm
import os
import math
import csv
import copy
import json
from typing import Type, Any, Callable, Union, List, Optional


__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
           'wide_resnet50_2', 'wide_resnet101_2']


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',
    'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
    'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
    'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
    'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}


def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d:
    """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: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)

import torch.nn.functional as F
import numpy as np

class L2pooling(nn.Module):
    def __init__(self, filter_size=5, stride=1, channels=None, pad_off=0):
        super(L2pooling, self).__init__()
        self.padding = (filter_size - 2 )//2
        self.stride = stride
        self.channels = channels
        a = np.hanning(filter_size)[1:-1]
        g = torch.Tensor(a[:,None]*a[None,:])
        g = g/torch.sum(g)
        self.register_buffer('filter', g[None,None,:,:].repeat((self.channels,1,1,1)))

    def forward(self, input):
        input = input**2
        out = F.conv2d(input, self.filter, stride=self.stride, padding=self.padding, groups=input.shape[1])
        return (out+1e-12).sqrt()
    

class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> 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: Tensor) -> Tensor:
        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):
    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
    # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
    # This variant is also known as ResNet V1.5 and improves accuracy according to
    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.

    expansion: int = 4

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.)) * 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: Tensor) -> Tensor:
        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: Type[Union[BasicBlock, Bottleneck]],
        layers: List[int],
        num_classes: int = 1000,
        zero_init_residual: bool = False,
        groups: int = 1,
        width_per_group: int = 64,
        replace_stride_with_dilation: Optional[List[bool]] = None,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer

        self.inplanes = 64
        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
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = norm_layer(self.inplanes)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        # self.maxpool = L2pooling(channels=64)
        
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
                                       dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
                                       dilate=replace_stride_with_dilation[1])
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
                                       dilate=replace_stride_with_dilation[2])
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        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.GroupNorm)):
                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)  # type: ignore[arg-type]
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)  # type: ignore[arg-type]

    def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int,
                    stride: int = 1, dilate: bool = False) -> nn.Sequential:
        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_impl(self, x: Tensor) -> Tensor:
        # See note [TorchScript super()]
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        l1 = x
        x = self.layer2(x)
        l2 = x
        x = self.layer3(x)
        l3 = x
        x = self.layer4(x)
        l4 = x
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x,l1,l2,l3,l4

    def forward(self, x: Tensor) -> Tensor:
        return self._forward_impl(x)


def _resnet(
    arch: str,
    block: Type[Union[BasicBlock, Bottleneck]],
    layers: List[int],
    pretrained: bool,
    progress: bool,
    **kwargs: Any
) -> ResNet:
    model = ResNet(block, layers, **kwargs)
    if pretrained:
        state_dict = torch.hub.load_state_dict_from_url(model_urls[arch],
                                              progress=progress)
        model.load_state_dict(state_dict)
    return model


def resnet18(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNet-18 model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
                   **kwargs)


def resnet34(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNet-34 model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
                   **kwargs)


def resnet50(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNet-50 model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
                   **kwargs)


def resnet101(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNet-101 model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress,
                   **kwargs)


def resnet152(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNet-152 model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
                   **kwargs)


def resnext50_32x4d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNeXt-50 32x4d model from
    `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
    """
    kwargs['groups'] = 32
    kwargs['width_per_group'] = 4
    return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
                   pretrained, progress, **kwargs)


def resnext101_32x8d(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""ResNeXt-101 32x8d model from
    `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
    """
    kwargs['groups'] = 32
    kwargs['width_per_group'] = 8
    return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3],
                   pretrained, progress, **kwargs)


def wide_resnet50_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""Wide ResNet-50-2 model from
    `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
    The model is the same as ResNet except for the bottleneck number of channels
    which is twice larger in every block. The number of channels in outer 1x1
    convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
    channels, and in Wide ResNet-50-2 has 2048-1024-2048.
    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
    """
    kwargs['width_per_group'] = 64 * 2
    return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3],
                   pretrained, progress, **kwargs)


def wide_resnet101_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet:
    r"""Wide ResNet-101-2 model from
    `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
    The model is the same as ResNet except for the bottleneck number of channels
    which is twice larger in every block. The number of channels in outer 1x1
    convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
    channels, and in Wide ResNet-50-2 has 2048-1024-2048.
    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
    """
    kwargs['width_per_group'] = 64 * 2
    return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3],
                   pretrained, progress, **kwargs)

class NestedTensor(object):
    def __init__(self, tensors, mask: Optional[Tensor]):
        self.tensors = tensors
        self.mask = mask

    def to(self, device):
        cast_tensor = self.tensors.to(device)
        mask = self.mask
        if mask is not None:
            assert mask is not None
            cast_mask = mask.to(device)
        else:
            cast_mask = None
        return NestedTensor(cast_tensor, cast_mask)

    def decompose(self):
        return self.tensors, self.mask

    def __repr__(self):
        return str(self.tensors)


class PositionEmbeddingSine(nn.Module):
    """
    This is a more standard version of the position embedding, very similar to the one
    used by the Attention is all you need paper, generalized to work on images.
    """
    def __init__(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None):
        super().__init__()
        self.num_pos_feats = num_pos_feats # 128 in dert
        self.temperature = temperature
        self.normalize = normalize
        if scale is not None and normalize is False:
            raise ValueError("normalize should be True if scale is passed")
        if scale is None:
            scale = 2 * math.pi
        self.scale = scale

    # def forward(self, tensor_list: NestedTensor):
    def forward(self, tensor_val):
        x = tensor_val
        # mask = tensor_list.mask # it has 1 for padding, so the important stuff is 0
        mask = torch.gt(torch.zeros(x.shape),0).to( x.device)[:,0,:,:]
        assert mask is not None
        not_mask = ~mask
        y_embed = not_mask.cumsum(1, dtype=torch.float32)
        x_embed = not_mask.cumsum(2, dtype=torch.float32)
        if self.normalize:
            eps = 1e-6
            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale

        dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)

        pos_x = x_embed[:, :, :, None] / dim_t
        pos_y = y_embed[:, :, :, None] / dim_t
        pos_x = torch.stack((pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4).flatten(3)
        pos_y = torch.stack((pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4).flatten(3)
        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
        return pos

class PositionEmbeddingLearned(nn.Module):
    """
    Absolute pos embedding, learned.
    """
    def __init__(self, num_pos_feats=256):
        super().__init__()
        self.row_embed = nn.Embedding(50, num_pos_feats)
        self.col_embed = nn.Embedding(50, num_pos_feats)
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.uniform_(self.row_embed.weight)
        nn.init.uniform_(self.col_embed.weight)

    def forward(self, tensor_list: NestedTensor):
        x = tensor_list.tensors
        h, w = x.shape[-2:]
        i = torch.arange(w, device=x.device)
        j = torch.arange(h, device=x.device)
        x_emb = self.col_embed(i)
        y_emb = self.row_embed(j)
        pos = torch.cat([
            x_emb.unsqueeze(0).repeat(h, 1, 1),
            y_emb.unsqueeze(1).repeat(1, w, 1),
        ], dim=-1).permute(2, 0, 1).unsqueeze(0).repeat(x.shape[0], 1, 1, 1)
        return pos


def build_position_encoding(args):
    N_steps = args.hidden_dim // 2
    if args.position_embedding in ('v2', 'sine'):
        # TODO find a better way of exposing other arguments
        position_embedding = PositionEmbeddingSine(N_steps, normalize=True)
    elif args.position_embedding in ('v3', 'learned'):
        position_embedding = PositionEmbeddingLearned(N_steps)
    else:
        raise ValueError(f"not supported {args.position_embedding}")

    return position_embedding


class Transformer(nn.Module):

    def __init__(self, d_model=256, nhead=8, num_encoder_layers=6,
                 num_decoder_layers=6, dim_feedforward=2048, dropout=0.1,
                 activation="relu", normalize_before=False,
                 return_intermediate_dec=False):
        super().__init__()

        encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward,
                                                dropout, activation, normalize_before)
        encoder_norm = nn.LayerNorm(d_model) if normalize_before else None
        self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)
        
        self._reset_parameters()


        self.nhead = nhead

    def _reset_parameters(self):
        for p in self.parameters():
            if p.dim() > 1:
                nn.init.xavier_uniform_(p)


    def forward(self, src , pos_embed):
        # flatten NxCxHxW to HWxNxC
        bs, c, h, w = src.shape
        src2 = src
        src = src.flatten(2).permute(2, 0, 1)
        pos_embed2 = pos_embed

        pos_embed = pos_embed.flatten(2).permute(2, 0, 1)
        
        memory = self.encoder(src, pos=pos_embed)
        
        return  memory.permute(1, 2, 0).view(bs, c, h, w)


class TransformerEncoder(nn.Module):

    def __init__(self, encoder_layer, num_layers, norm=None):
        super().__init__()
        self.layers = _get_clones(encoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm

    def forward(self, src,
                mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        output = src

        for layer in self.layers:
            output = layer(output, src_mask=mask,
                           src_key_padding_mask=src_key_padding_mask, pos=pos)

        if self.norm is not None:
            output = self.norm(output)

        return output




class TransformerEncoderLayer(nn.Module):

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                 activation="relu", normalize_before=False):
        super().__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        # Implementation of Feedforward model
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)

        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos

    def forward_post(self,
                     src,
                     src_mask: Optional[Tensor] = None,
                     src_key_padding_mask: Optional[Tensor] = None,
                     pos: Optional[Tensor] = None):
        q = k = self.with_pos_embed(src, pos)
        src2 = self.self_attn(q, k, value=src, attn_mask=src_mask,
                              key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src

    def forward_pre(self, src,
                    src_mask: Optional[Tensor] = None,
                    src_key_padding_mask: Optional[Tensor] = None,
                    pos: Optional[Tensor] = None):
        src2 = self.norm1(src)
        q = k = self.with_pos_embed(src2, pos)
        src2 = self.self_attn(q, k, value=src2, attn_mask=src_mask,
                              key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src2 = self.norm2(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src2))))
        src = src + self.dropout2(src2)
        return src

    def forward(self, src,
                src_mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        if self.normalize_before:
            return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
        return self.forward_post(src, src_mask, src_key_padding_mask, pos)



def _get_clones(module, N):
    return nn.ModuleList([copy.deepcopy(module) for i in range(N)])


def build_transformer(args):
    return Transformer(
        d_model=args.hidden_dim,
        dropout=args.dropout,
        nhead=args.nheads,
        dim_feedforward=args.dim_feedforward,
        num_encoder_layers=args.enc_layers,
        num_decoder_layers=args.dec_layers,
        normalize_before=args.pre_norm,
        return_intermediate_dec=True,
    )


def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == "relu":
        return F.relu
    if activation == "gelu":
        return F.gelu
    if activation == "glu":
        return F.glu
    raise RuntimeError(F"activation should be relu/gelu, not {activation}.")
    
    

if __name__=='__main__':
    
    
    d_modelt=1024
    nheadt=8
    num_encoder_layerst=2
    dim_feedforwardt=1024
    dropout=0.1
    normalize_beforet=False
        
        
    transformer = Transformer(d_model=d_modelt,nhead=nheadt,num_encoder_layers=num_encoder_layerst,
    dim_feedforward=dim_feedforwardt,normalize_before=normalize_beforet)
    
    hidden_dim = d_modelt
    pos_enc = PositionEmbeddingSine(hidden_dim // 2, normalize=True)
    
    src = torch.rand(2, hidden_dim, 19, 29)
    pos_add = pos_enc(src)

    out = transformer(src,pos_embed = pos_add)
    print(torch.sum(out),out.shape)


class L2pooling(nn.Module):
	def __init__(self, filter_size=5, stride=1, channels=None, pad_off=0):
		super(L2pooling, self).__init__()
		self.padding = (filter_size - 2 )//2
		self.stride = stride
		self.channels = channels
		a = np.hanning(filter_size)[1:-1]
		g = torch.Tensor(a[:,None]*a[None,:])
		g = g/torch.sum(g)
		self.register_buffer('filter', g[None,None,:,:].repeat((self.channels,1,1,1)))
	def forward(self, input):
		input = input**2
		out = F.conv2d(input, self.filter, stride=self.stride, padding=self.padding, groups=input.shape[1])
		return (out+1e-12).sqrt()
	
class Net(nn.Module):
	def __init__(self,cfg,device):
		super(Net, self).__init__()
		
		
		self.device = device
		
		self.cfg = cfg
		self.L2pooling_l1 = L2pooling(channels=256)
		self.L2pooling_l2 = L2pooling(channels=512)
		self.L2pooling_l3 = L2pooling(channels=1024)
		self.L2pooling_l4 = L2pooling(channels=2048)
		


			
		if cfg.network =='resnet50':
			dim_modelt = 3840
			modelpretrain = models.resnet50(pretrained=True)

		elif cfg.network =='resnet34':
			modelpretrain = models.resnet34(pretrained=True)
			dim_modelt = 960
			self.L2pooling_l1 = L2pooling(channels=64)
			self.L2pooling_l2 = L2pooling(channels=128)
			self.L2pooling_l3 = L2pooling(channels=256)
			self.L2pooling_l4 = L2pooling(channels=512)
		elif cfg.network == 'resnet18':
			modelpretrain = models.resnet18(pretrained=True)
			dim_modelt = 960
			self.L2pooling_l1 = L2pooling(channels=64)
			self.L2pooling_l2 = L2pooling(channels=128)
			self.L2pooling_l3 = L2pooling(channels=256)
			self.L2pooling_l4 = L2pooling(channels=512)


		torch.save(modelpretrain.state_dict(), 'modelpretrain')
		
		self.model = resnet50()
		self.model.load_state_dict(torch.load('modelpretrain'), strict=True)

		self.dim_modelt = dim_modelt

		os.remove("modelpretrain")
		



		nheadt=cfg.nheadt
		num_encoder_layerst=cfg.num_encoder_layerst
		dim_feedforwardt=cfg.dim_feedforwardt
		ddropout=0.5
		normalize =True
			
			
		self.transformer = Transformer(d_model=dim_modelt,nhead=nheadt,
									   num_encoder_layers=num_encoder_layerst,
									   dim_feedforward=dim_feedforwardt,
									   normalize_before=normalize,
									   dropout = ddropout)
		

		self.position_embedding = PositionEmbeddingSine(dim_modelt // 2, normalize=True)




		self.fc2 = nn.Linear(dim_modelt, self.model.fc.in_features) 
		self.fc = nn.Linear(self.model.fc.in_features*2, 1) 

		
		
		self.ReLU = nn.ReLU()
		self.avg7 = nn.AvgPool2d((7, 7))
		self.avg8 = nn.AvgPool2d((8, 8))
		self.avg4 = nn.AvgPool2d((4, 4))
		self.avg2 = nn.AvgPool2d((2, 2))
		
			   
		
		self.drop2d = nn.Dropout(p=0.1)
		self.consistency = nn.L1Loss()
		
		
		
		

	def forward(self, x):
		self.pos_enc_1 = self.position_embedding(torch.ones(1, self.dim_modelt, 7, 7).to(self.device))
		self.pos_enc = self.pos_enc_1.repeat(x.shape[0],1,1,1).contiguous()

		out,layer1,layer2,layer3,layer4 = self.model(x) 

		layer1_t = self.avg8(self.drop2d(self.L2pooling_l1(F.normalize(layer1,dim=1, p=2))))
		layer2_t = self.avg4(self.drop2d(self.L2pooling_l2(F.normalize(layer2,dim=1, p=2))))
		layer3_t = self.avg2(self.drop2d(self.L2pooling_l3(F.normalize(layer3,dim=1, p=2))))
		layer4_t =           self.drop2d(self.L2pooling_l4(F.normalize(layer4,dim=1, p=2)))
		layers = torch.cat((layer1_t,layer2_t,layer3_t,layer4_t),dim=1)

		out_t_c = self.transformer(layers,self.pos_enc)
		out_t_o = torch.flatten(self.avg7(out_t_c),start_dim=1)
		out_t_o = self.fc2(out_t_o)
		layer4_o = self.avg7(layer4)
		layer4_o = torch.flatten(layer4_o,start_dim=1)
		predictionQA = self.fc(torch.flatten(torch.cat((out_t_o,layer4_o),dim=1),start_dim=1))
		
		# =============================================================================
		# =============================================================================


		# fout,flayer1,flayer2,flayer3,flayer4 = self.model(torch.flip(x, [3])) 
		# flayer1_t = self.avg8( self.L2pooling_l1(F.normalize(flayer1,dim=1, p=2)))
		# flayer2_t = self.avg4( self.L2pooling_l2(F.normalize(flayer2,dim=1, p=2)))
		# flayer3_t = self.avg2( self.L2pooling_l3(F.normalize(flayer3,dim=1, p=2)))
		# flayer4_t =            self.L2pooling_l4(F.normalize(flayer4,dim=1, p=2))
		# flayers = torch.cat((flayer1_t,flayer2_t,flayer3_t,flayer4_t),dim=1)
		# fout_t_c = self.transformer(flayers,self.pos_enc)
		# fout_t_o = torch.flatten(self.avg7(fout_t_c),start_dim=1)
		# fout_t_o = (self.fc2(fout_t_o))
		# flayer4_o = self.avg7(flayer4)
		# flayer4_o = torch.flatten(flayer4_o,start_dim=1)
		# fpredictionQA =  (self.fc(torch.flatten(torch.cat((fout_t_o,flayer4_o),dim=1),start_dim=1)))

		
		# consistloss1 = self.consistency(out_t_c,fout_t_c.detach())
		# consistloss2 = self.consistency(layer4,flayer4.detach())
		# consistloss = 1*(consistloss1+consistloss2)
				
		return predictionQA, torch.flatten(torch.cat((out_t_o,layer4_o),dim=1),start_dim=1)