rm center loss & ring loss

torchreid/losses/__init__.py

@@ -4,8 +4,6 @@ from __future__ import print_function
 
 from .cross_entropy_loss import CrossEntropyLoss
 from .hard_mine_triplet_loss import TripletLoss
-from .center_loss import CenterLoss
-from .ring_loss import RingLoss
 
 
 def DeepSupervision(criterion, xs, y):

torchreid/losses/center_loss.py

@@ -1,56 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-
-import warnings
-
-import torch
-import torch.nn as 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=10, feat_dim=2, use_gpu=True):
-        super(CenterLoss, self).__init__()
-        warnings.warn('This method is deprecated')
-        self.num_classes = num_classes
-        self.feat_dim = feat_dim
-        self.use_gpu = use_gpu
-
-        if self.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).
-        """
-        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()
-        if self.use_gpu: classes = classes.cuda()
-        labels = labels.unsqueeze(1).expand(batch_size, self.num_classes)
-        mask = labels.eq(classes.expand(batch_size, self.num_classes))
-
-        dist = []
-        for i in range(batch_size):
-            value = distmat[i][mask[i]]
-            value = value.clamp(min=1e-12, max=1e+12) # for numerical stability
-            dist.append(value)
-        dist = torch.cat(dist)
-        loss = dist.mean()
-
-        return loss

torchreid/losses/ring_loss.py

@@ -1,23 +0,0 @@
-from __future__ import absolute_import
-from __future__ import division
-
-import warnings
-
-import torch
-import torch.nn as nn
-
-
-class RingLoss(nn.Module):
-    """Ring loss.
-    
-    Reference:
-    Zheng et al. Ring loss: Convex Feature Normalization for Face Recognition. CVPR 2018.
-    """
-    def __init__(self):
-        super(RingLoss, self).__init__()
-        warnings.warn('This method is deprecated')
-        self.radius = nn.Parameter(torch.ones(1, dtype=torch.float))
-
-    def forward(self, x):
-        loss = ((x.norm(p=2, dim=1) - self.radius)**2).mean()
-        return loss