diff --git a/data/base_dataset.py b/data/base_dataset.py
index 4a010c52..9948bfc5 100644
--- a/data/base_dataset.py
+++ b/data/base_dataset.py
@@ -16,7 +16,7 @@ def get_transform(opt):
     transform_list = []
     if opt.resize_or_crop == 'resize_and_crop':
         osize = [opt.loadSizeX, opt.loadSizeY]
-        transform_list.append(transforms.Scale(osize, Image.BICUBIC))
+        transform_list.append(transforms.Resize(osize, Image.BICUBIC))
         transform_list.append(transforms.RandomCrop(opt.fineSize))
     elif opt.resize_or_crop == 'crop':
         transform_list.append(transforms.RandomCrop(opt.fineSize))
diff --git a/data/custom_dataset_data_loader.py b/data/custom_dataset_data_loader.py
index 1bf1dc22..1d2441c3 100644
--- a/data/custom_dataset_data_loader.py
+++ b/data/custom_dataset_data_loader.py
@@ -13,6 +13,7 @@ def CreateDataset(opt):
     elif opt.dataset_mode == 'single':
         from data.single_dataset import SingleDataset
         dataset = SingleDataset()
+        dataset.initialize(opt)
     else:
         raise ValueError("Dataset [%s] not recognized." % opt.dataset_mode)
 
diff --git a/models/test_model.py b/models/test_model.py
index a1316766..5c2d83ed 100644
--- a/models/test_model.py
+++ b/models/test_model.py
@@ -1,3 +1,4 @@
+import torch
 from torch.autograd import Variable
 from collections import OrderedDict
 import util.util as util
@@ -33,8 +34,9 @@ def set_input(self, input):
         self.image_paths = input['A_paths']
 
     def test(self):
-        self.real_A = Variable(self.input_A, volatile=True)
-        self.fake_B = self.netG.forward(self.real_A)
+        with torch.no_grad():
+            self.real_A = Variable(self.input_A)
+            self.fake_B = self.netG.forward(self.real_A)
 
     # get image paths
     def get_image_paths(self):