import torch
import torch.nn as nn

class SimpleConLoss(nn.Module):
  def __init__(self, m=2.0):
    super(SimpleConLoss, self).__init__()  # pre 3.3 syntax
    self.m = m  # margin or radius

  def forward(self, y1, y2, d=0):
    # d = 0 means y1 and y2 are supposed to be same
    # d = 1 means y1 and y2 are supposed to be different
    
    euc_dist = nn.functional.pairwise_distance(y1, y2)

    if d == 0:
      return torch.mean(torch.pow(euc_dist, 2))  # distance squared
    else:  # d == 1
      delta = self.m - euc_dist  # sort of reverse distance
      delta = torch.clamp(delta, min=0.0, max=None)
      return torch.mean(torch.pow(delta, 2))  # mean over all rows

class SupConLoss(nn.Module):
    """Supervised Contrastive Learning: https://arxiv.org/pdf/2004.11362.pdf.
    It also supports the unsupervised contrastive loss in SimCLR"""
    def __init__(self, temperature=0.07, contrast_mode='all',
                 base_temperature=0.07, device = 'cpu'):
        super(SupConLoss, self).__init__()
        self.temperature = temperature
        self.contrast_mode = contrast_mode
        self.base_temperature = base_temperature
        self.device = device

    def forward(self, features, labels=None):
        """Compute loss for model. If both `labels` and `mask` are None,
        it degenerates to SimCLR unsupervised loss:
        https://arxiv.org/pdf/2002.05709.pdf
        Args:
            features: hidden vector of shape [bsz, n_views, ...].
            labels: ground truth of shape [bsz].
            mask: contrastive mask of shape [bsz, bsz], mask_{i,j}=1 if sample j
                has the same class as sample i. Can be asymmetric.
        Returns:
            A loss scalar.
        """
        device = self.device
        
        if len(features.shape) < 3:
            raise ValueError('`features` needs to be [bsz, n_views, ...],'
                             'at least 3 dimensions are required')
        if len(features.shape) > 3:
            features = features.view(features.shape[0], features.shape[1], -1)

        batch_size = features.shape[0]
        
        if labels is None:
            # mask = torch.eye(batch_size, dtype=torch.float32)
            mask = torch.eye(batch_size, dtype=torch.float32).to(device)
        elif labels is not None:
            labels = labels.contiguous().view(-1, 1)
            if labels.shape[0] != batch_size:
                raise ValueError('Num of labels does not match num of features')
            mask = torch.eq(labels, labels.T).float().to(device) # Creates a mask of comparisons between all pairs of samples
            # mask = torch.eq(labels, labels.T).float() # Creates a mask of comparisons between all pairs of samples


        contrast_count = features.shape[1]
        contrast_feature = torch.cat(torch.unbind(features, dim=1), dim=0) 
        
        if self.contrast_mode == 'one':
            anchor_feature = features[:, 0]
            anchor_count = 1
        elif self.contrast_mode == 'all':
            anchor_feature = contrast_feature
            anchor_count = contrast_count
        else:
            raise ValueError('Unknown mode: {}'.format(self.contrast_mode))

        # compute logits
        anchor_dot_contrast = torch.div(
            torch.matmul(anchor_feature, contrast_feature.T),
            self.temperature)

        # for numerical stability
        logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
        logits = anchor_dot_contrast - logits_max.detach()

        # tile mask
        mask = mask.repeat(anchor_count, contrast_count)
        # mask-out self-contrast cases
        logits_mask = torch.scatter(
            torch.ones_like(mask),
            1,
            torch.arange(batch_size * anchor_count).view(-1, 1).to(device),
            0
        )
        mask = mask * logits_mask

        # compute log_prob
        exp_logits = torch.exp(logits) * logits_mask
        log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True))

        # compute mean of log-likelihood over positive
        mean_log_prob_pos = (mask * log_prob).sum(1) / mask.sum(1)

        # loss
        # loss = - (self.temperature / self.base_temperature) * mean_log_prob_pos
        loss = - mean_log_prob_pos
        loss = loss.view(anchor_count, batch_size).mean()

        return loss

if __name__ == '__main__':

    criterion = SupConLoss()

    features = torch.randn(3, 2, 1)
    labels = torch.randint(0, 3, (3,))

    print("features")
    print(features)
    print("labels")
    print(labels)

    criterion(features, labels)