# encoding: utf-8
"""
@author:  liaoxingyu
@contact: sherlockliao01@gmail.com
"""
import torch
from torch import nn


class CenterLoss(nn.Module):
    """Center loss.
    Reference:
    Wen et al. A Discriminative Feature Learning Approach for Deep Face Recognition. ECCV 2016.
    Args:
        num_classes (int): number of classes.
        feat_dim (int): feature dimension.
    """

    def __init__(self, num_classes=751, feat_dim=2048, use_gpu=True):
        super(CenterLoss, self).__init__()
        self.num_classes,self.feat_dim = num_classes, feat_dim

        if use_gpu: self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim).cuda())
        else:       self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim))

    def forward(self, x, labels):
        """
        Args:
            x: feature matrix with shape (batch_size, feat_dim).
            labels: ground truth labels with shape (num_classes).
        """
        assert x.size(0) == labels.size(0), "features.size(0) is not equal to labels.size(0)"

        batch_size = x.size(0)
        distmat = torch.pow(x, 2).sum(dim=1, keepdim=True).expand(batch_size, self.num_classes) + \
                  torch.pow(self.centers, 2).sum(dim=1, keepdim=True).expand(self.num_classes, batch_size).t()
        distmat.addmm_(1, -2, x, self.centers.t())

        classes = torch.arange(self.num_classes).long()
        classes = classes.to(x.device)
        labels = labels.unsqueeze(1).expand(batch_size, self.num_classes)
        mask = labels.eq(classes.expand(batch_size, self.num_classes))

        dist = distmat * mask.float()
        loss = dist.clamp(min=1e-12, max=1e+12).sum() / batch_size
        return loss