diff --git a/reco_encoder/model/model.py b/reco_encoder/model/model.py
index 339a32b..323fc98 100644
--- a/reco_encoder/model/model.py
+++ b/reco_encoder/model/model.py
@@ -57,7 +57,7 @@ def __init__(self, layer_sizes, nl_type='selu', is_constrained=True, dp_drop_pro
     self.encode_w = nn.ParameterList(
       [nn.Parameter(torch.rand(layer_sizes[i + 1], layer_sizes[i])) for i in range(len(layer_sizes) - 1)])
     for ind, w in enumerate(self.encode_w):
-      weight_init.xavier_uniform(w)
+      weight_init.xavier_uniform_(w)
 
     self.encode_b = nn.ParameterList(
       [nn.Parameter(torch.zeros(layer_sizes[i + 1])) for i in range(len(layer_sizes) - 1)])
@@ -69,7 +69,7 @@ def __init__(self, layer_sizes, nl_type='selu', is_constrained=True, dp_drop_pro
       self.decode_w = nn.ParameterList(
       [nn.Parameter(torch.rand(reversed_enc_layers[i + 1], reversed_enc_layers[i])) for i in range(len(reversed_enc_layers) - 1)])
       for ind, w in enumerate(self.decode_w):
-        weight_init.xavier_uniform(w)
+        weight_init.xavier_uniform_(w)
     self.decode_b = nn.ParameterList(
       [nn.Parameter(torch.zeros(reversed_enc_layers[i + 1])) for i in range(len(reversed_enc_layers) - 1)])
 
diff --git a/run.py b/run.py
index 3936781..05d5fe1 100644
--- a/run.py
+++ b/run.py
@@ -71,8 +71,8 @@ def do_eval(encoder, evaluation_data_layer):
     targets = Variable(eval.cuda().to_dense() if use_gpu else eval.to_dense())
     outputs = encoder(inputs)
     loss, num_ratings = model.MSEloss(outputs, targets)
-    total_epoch_loss += loss.data[0]
-    denom += num_ratings.data[0]
+    total_epoch_loss += loss.item()
+    denom += num_ratings.item()
   return sqrt(total_epoch_loss / denom)
 
 def log_var_and_grad_summaries(logger, layers, global_step, prefix, log_histograms=False):
@@ -195,7 +195,7 @@ def main():
       loss.backward()
       optimizer.step()
       global_step += 1
-      t_loss += loss.data[0]
+      t_loss += loss.item()
       t_loss_denom += 1
 
       if i % args.summary_frequency == 0:
@@ -209,7 +209,7 @@ def main():
           log_var_and_grad_summaries(logger, rencoder.decode_w, global_step, "Decode_W")
         log_var_and_grad_summaries(logger, rencoder.decode_b, global_step, "Decode_b")
 
-      total_epoch_loss += loss.data[0]
+      total_epoch_loss += loss.item()
       denom += 1
 
       #if args.aug_step > 0 and i % args.aug_step == 0 and i > 0:
diff --git a/test/test_model.py b/test/test_model.py
index 6f54f5f..ab72385 100644
--- a/test/test_model.py
+++ b/test/test_model.py
@@ -31,7 +31,7 @@ def test_CPU(self):
         loss = loss / num_ratings
         loss.backward()
         optimizer.step()
-        print('[%d, %5d] loss: %.7f' % (epoch, i, loss.data[0]))
+        print('[%d, %5d] loss: %.7f' % (epoch, i, loss.item()))
 
   def test_GPU(self):
     print("iRecAutoEncoderTest Test on GPU started")
@@ -56,7 +56,7 @@ def test_GPU(self):
         loss = loss / num_ratings
         loss.backward()
         optimizer.step()
-        total_epoch_loss += loss.data[0]
+        total_epoch_loss += loss.item()
         denom += 1
       print("Total epoch {} loss: {}".format(epoch, total_epoch_loss/denom))
 
@@ -81,7 +81,7 @@ def test_CPU(self):
         loss = loss / num_ratings
         loss.backward()
         optimizer.step()
-        print('[%d, %5d] loss: %.7f' % (epoch, i, loss.data[0]))
+        print('[%d, %5d] loss: %.7f' % (epoch, i, loss.item()))
         if i == 5: # too much compute for CPU
           break
 
@@ -108,7 +108,7 @@ def test_GPU(self):
         loss = loss / num_ratings
         loss.backward()
         optimizer.step()
-        total_epoch_loss += loss.data[0]
+        total_epoch_loss += loss.item()
         denom += 1
       print("Total epoch {} loss: {}".format(epoch, total_epoch_loss / denom))