import math
from functools import partial

import torch
import torch.nn as nn
import torch.nn.functional as F


def get_inplanes():
    return [64, 128, 256, 512]


def conv3x3x3(in_planes, out_planes, stride=1):
    return nn.Conv3d(in_planes,
                     out_planes,
                     kernel_size=3,
                     stride=stride,
                     padding=1,
                     bias=False)


def conv1x1x1(in_planes, out_planes, stride=1):
    return nn.Conv3d(in_planes,
                     out_planes,
                     kernel_size=1,
                     stride=stride,
                     bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1, downsample=None):
        super().__init__()

        self.conv1 = conv3x3x3(in_planes, planes, stride)
        self.bn1 = nn.BatchNorm3d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3x3(planes, planes)
        self.bn2 = nn.BatchNorm3d(planes)
        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)

        if self.downsample is not None:
            residual = self.downsample(x)

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

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, in_planes, planes, stride=1, downsample=None):
        super().__init__()

        self.conv1 = conv1x1x1(in_planes, planes)
        self.bn1 = nn.BatchNorm3d(planes)
        self.conv2 = conv3x3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm3d(planes)
        self.conv3 = conv1x1x1(planes, planes * self.expansion)
        self.bn3 = nn.BatchNorm3d(planes * self.expansion)
        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 ResNet(nn.Module):

    def __init__(self,
                 block,
                 layers,
                 block_inplanes,
                 n_input_channels=3,
                 conv1_t_size=7,
                 conv1_t_stride=1,
                 no_max_pool=False,
                 shortcut_type='B',
                 widen_factor=1.0):
        super().__init__()

        block_inplanes = [int(x * widen_factor) for x in block_inplanes]

        self.in_planes = block_inplanes[0]
        self.no_max_pool = no_max_pool

        self.conv1 = nn.Conv3d(n_input_channels,
                               self.in_planes,
                               kernel_size=(conv1_t_size, 7, 7),
                               stride=(conv1_t_stride, 2, 2),
                               padding=(conv1_t_size // 2, 3, 3),
                               bias=False)
        self.bn1 = nn.BatchNorm3d(self.in_planes)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool3d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, block_inplanes[0], layers[0],
                                       shortcut_type)
        self.layer2 = self._make_layer(block,
                                       block_inplanes[1],
                                       layers[1],
                                       shortcut_type,
                                       stride=2)
        self.layer3 = self._make_layer(block,
                                       block_inplanes[2],
                                       layers[2],
                                       shortcut_type,
                                       stride=2)
        self.layer4 = self._make_layer(block,
                                       block_inplanes[3],
                                       layers[3],
                                       shortcut_type,
                                       stride=2)

        self.avgpool = nn.AdaptiveAvgPool3d((1, 1, 1))
        # self.fc = nn.Linear(block_inplanes[3] * block.expansion, n_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv3d):
                nn.init.kaiming_normal_(m.weight,
                                        mode='fan_out',
                                        nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm3d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _downsample_basic_block(self, x, planes, stride):
        out = F.avg_pool3d(x, kernel_size=1, stride=stride)
        zero_pads = torch.zeros(out.size(0), planes - out.size(1), out.size(2),
                                out.size(3), out.size(4))
        if isinstance(out.data, torch.cuda.FloatTensor):
            zero_pads = zero_pads.cuda()

        out = torch.cat([out.data, zero_pads], dim=1)

        return out

    def _make_layer(self, block, planes, blocks, shortcut_type, stride=1):
        downsample = None
        if stride != 1 or self.in_planes != planes * block.expansion:
            if shortcut_type == 'A':
                downsample = partial(self._downsample_basic_block,
                                     planes=planes * block.expansion,
                                     stride=stride)
            else:
                downsample = nn.Sequential(
                    conv1x1x1(self.in_planes, planes * block.expansion, stride),
                    nn.BatchNorm3d(planes * block.expansion))

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

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        if not self.no_max_pool:
            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)
        return x


def generate_model(model_depth, **kwargs):
    assert model_depth in [10, 18, 34, 50, 101, 152, 200]

    if model_depth == 10:
        model = ResNet(BasicBlock, [1, 1, 1, 1], get_inplanes(), **kwargs)
    elif model_depth == 18:
        model = ResNet(BasicBlock, [2, 2, 2, 2], get_inplanes(), **kwargs)
    elif model_depth == 34:
        model = ResNet(BasicBlock, [3, 4, 6, 3], get_inplanes(), **kwargs)
    elif model_depth == 50:
        model = ResNet(Bottleneck, [3, 4, 6, 3], get_inplanes(), **kwargs)
    elif model_depth == 101:
        model = ResNet(Bottleneck, [3, 4, 23, 3], get_inplanes(), **kwargs)
    elif model_depth == 152:
        model = ResNet(Bottleneck, [3, 8, 36, 3], get_inplanes(), **kwargs)
    elif model_depth == 200:
        model = ResNet(Bottleneck, [3, 24, 36, 3], get_inplanes(), **kwargs)

    return model



class Bottleneck(nn.Module):
    def __init__(self, inplanes, planes, stride=1):
        super(Bottleneck, self).__init__()
        self.bn1 = nn.BatchNorm3d(inplanes)
        self.relu = nn.ReLU()
        self.bn2 = nn.BatchNorm3d(planes)
        self.conv1 = nn.Conv3d(inplanes, planes, kernel_size=3, stride=stride, padding=1)
        self.conv2 = nn.Conv3d(planes, planes, kernel_size=3, stride=stride, padding=1)
        self.stride = stride

    def forward(self, x):
        residual = x
        out = self.bn1(x)
        out = self.relu(out)
        out = self.conv1(out)
        out = self.bn2(x)
        out = self.relu(out)
        out = self.conv2(out)
        out += residual
        return out

class ResNet3D(nn.Module):
    def __init__(self, num_classes=2, input_shape=(1,110,110,110)): # input: input_shape:	[num_of_filters, kernel_size] (e.g. [256, 25])
        super(ResNet3D, self).__init__()
        #stage 1
        self.conv1 = nn.Sequential(
            nn.Conv3d(
            in_channels=input_shape[0],
            out_channels=32,
            kernel_size=(3,3,3),
            padding=1
            ),
            nn.BatchNorm3d(32),
            nn.ReLU(),
            nn.Conv3d(
            in_channels=32,
            out_channels=32,
            kernel_size=(3,3,3),
            padding=1
            ),
            nn.BatchNorm3d(32),
            nn.ReLU(),
            nn.Conv3d(
            in_channels=32,
            out_channels=64,
            kernel_size=(3,3,3),
            stride=2,
            padding=1
            )
        )
        #stage 2
        self.bot2=Bottleneck(64,64,1)
        #stage 3
        self.bot3=Bottleneck(64,64,1)
        #stage 4
        self.conv4=nn.Sequential(
            nn.BatchNorm3d(64),
            nn.Conv3d(
            in_channels=64,        # input height
            out_channels=64,       # n_filters
            kernel_size=(3,3,3),          # filter size
            padding=1,
            stride=2
            )
        )
        #stage 5
        self.bot5=Bottleneck(64,64,1)
        #stage 6
        self.bot6=Bottleneck(64,64,1)
        #stage 7
        self.conv7=nn.Sequential(
            nn.BatchNorm3d(64),
            nn.Conv3d(
            in_channels=64,        # input height
            out_channels=128,       # n_filters
            kernel_size=(3,3,3),          # filter size
            padding=1,
            stride=2
            )
        )
        #stage 8
        self.bot8=Bottleneck(128,128,1)

        #stage 9
        self.bot9=Bottleneck(128,128,1)

        #stage 10
        self.conv10=nn.Sequential(
            nn.MaxPool3d(kernel_size=(7,7,7)))

        fc1_output_features=128
        self.fc1 = nn.Sequential(
             nn.Linear(512, 128),
             nn.ReLU()
        )

        self.fc2 = nn.Sequential(nn.Linear(fc1_output_features, 3))

    def forward(self, x, drop_prob=0.8):
        x = self.conv1(x)
        #print(x.shape)
        x = self.bot2(x)
        #print(x.shape)
        x = self.bot3(x)
        #print(x.shape)
        x = self.conv4(x)
        #print(x.shape)
        x = self.bot5(x)
        #print(x.shape)
        x = self.bot6(x)
        #print(x.shape)
        x = self.conv7(x)
        #print(x.shape)
        x = self.bot8(x)
        #print(x.shape)
        x = self.bot9(x)
        #print(x.shape)
        x = self.conv10(x)
        #print(x.shape)
        x = x.view(x.size(0), -1) # flatten the output of conv2 to (batch_size, num_filter * w * h)
        #print(x.shape)
        # x = self.fc1(x)
        # x = self.fc2(x)
        #prob = self.out(x) # probability
        return x

def main():
    # Create a random 3D tensor with dimensions (C, D, H, W)
    channels = 3
    depth = 64
    height = 128
    width = 128
    random_tensor = torch.randn((channels, depth, height, width))  # Replace with torch.rand() if you want values in [0, 1)

    # You can also reshape the tensor if needed (example: 1 x C x D x H x W)
    tensor_data = random_tensor.unsqueeze(0)  # Add batch dimension (1, C, D, H, W)

    # Instantiate the ResNet model
    model_depth = 18  # Replace with the desired ResNet model depth (e.g., 18, 34, 50, etc.)
    model = generate_model(10, n_input_channels=1, n_classes=1000)  # Example number of classes

    # Pass the tensor through the ResNet model
    model.eval()
    with torch.no_grad():
        output = model(tensor_data)

    print("Model output shape:", output.shape)

if __name__ == "__main__":
    main()