typo fix

fxia22 · Apr 17, 2019 · f0c2430 · f0c2430
1 parent 1ed7901
commit f0c2430
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 7 deletions.
diff --git a/pointnet/model.py b/pointnet/model.py
@@ -174,7 +174,7 @@ def forward(self, x):
         x = x.view(batchsize, n_pts, self.k)
         return x, trans, trans_feat
 
-def feature_transform_reguliarzer(trans):
+def feature_transform_regularizer(trans):
     d = trans.size()[1]
     batchsize = trans.size()[0]
     I = torch.eye(d)[None, :, :]
@@ -188,13 +188,13 @@ def feature_transform_reguliarzer(trans):
     trans = STN3d()
     out = trans(sim_data)
     print('stn', out.size())
-    print('loss', feature_transform_reguliarzer(out))
+    print('loss', feature_transform_regularizer(out))
 
     sim_data_64d = Variable(torch.rand(32, 64, 2500))
     trans = STNkd(k=64)
     out = trans(sim_data_64d)
     print('stn64d', out.size())
-    print('loss', feature_transform_reguliarzer(out))
+    print('loss', feature_transform_regularizer(out))
 
     pointfeat = PointNetfeat(global_feat=True)
     out, _, _ = pointfeat(sim_data)

diff --git a/utils/train_classification.py b/utils/train_classification.py
@@ -7,7 +7,7 @@
 import torch.optim as optim
 import torch.utils.data
 from pointnet.dataset import ShapeNetDataset, ModelNetDataset
-from pointnet.model import PointNetCls, feature_transform_reguliarzer
+from pointnet.model import PointNetCls, feature_transform_regularizer
 import torch.nn.functional as F
 from tqdm import tqdm
 
@@ -109,7 +109,7 @@
         pred, trans, trans_feat = classifier(points)
         loss = F.nll_loss(pred, target)
         if opt.feature_transform:
-            loss += feature_transform_reguliarzer(trans_feat) * 0.001
+            loss += feature_transform_regularizer(trans_feat) * 0.001
         loss.backward()
         optimizer.step()
         pred_choice = pred.data.max(1)[1]

diff --git a/utils/train_segmentation.py b/utils/train_segmentation.py
@@ -7,7 +7,7 @@
 import torch.optim as optim
 import torch.utils.data
 from pointnet.dataset import ShapeNetDataset
-from pointnet.model import PointNetDenseCls, feature_transform_reguliarzer
+from pointnet.model import PointNetDenseCls, feature_transform_regularizer
 import torch.nn.functional as F
 from tqdm import tqdm
 import numpy as np
@@ -91,7 +91,7 @@
         #print(pred.size(), target.size())
         loss = F.nll_loss(pred, target)
         if opt.feature_transform:
-            loss += feature_transform_reguliarzer(trans_feat) * 0.001
+            loss += feature_transform_regularizer(trans_feat) * 0.001
         loss.backward()
         optimizer.step()
         pred_choice = pred.data.max(1)[1]