import torch
import torch.nn as nn
import torchvision


class HopeNet(nn.Module):
    # Hopenet with 3 output layers for yaw, pitch and roll
    # Predicts Euler angles by binning and regression with the expected value
    def __init__(self, block, layers, num_bins):
        super(HopeNet, self).__init__()
        if block == 'resnet':
            block = torchvision.models.resnet.Bottleneck
        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.AvgPool2d(7)
        self.fc_yaw = nn.Linear(512 * block.expansion, num_bins)
        self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
        self.fc_roll = nn.Linear(512 * block.expansion, num_bins)

        self.idx_tensor = torch.arange(66).float()

    def _make_layer(self, block, planes, blocks, stride=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),
                nn.BatchNorm2d(planes * block.expansion),
            )

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

    @staticmethod
    def softmax_temperature(tensor, temperature):
        result = torch.exp(tensor / temperature)
        result = torch.div(result, torch.sum(result, 1).unsqueeze(1).expand_as(result))
        return result

    def bin2degree(self, predict):
        predict = self.softmax_temperature(predict, 1)
        return torch.sum(predict * self.idx_tensor.type_as(predict), 1) * 3 - 99

    def forward(self, x):
        x = self.relu(self.bn1(self.conv1(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)
        pre_yaw = self.fc_yaw(x)
        pre_pitch = self.fc_pitch(x)
        pre_roll = self.fc_roll(x)

        yaw = self.bin2degree(pre_yaw)
        pitch = self.bin2degree(pre_pitch)
        roll = self.bin2degree(pre_roll)
        return yaw, pitch, roll