diff --git a/docs/tutorial/interfaces.md b/docs/tutorial/interfaces.md
index b5a4f1ad069..2578af5d4de 100644
--- a/docs/tutorial/interfaces.md
+++ b/docs/tutorial/interfaces.md
@@ -129,8 +129,8 @@ Use CPU:
 
 Use GPU and specify its gpu_id:
 
-    caffe.set_mode_gpu();
     caffe.set_device(gpu_id);
+    caffe.set_mode_gpu();
 
 #### Create a network and access its layers and blobs
 
diff --git a/python/train.py b/python/train.py
index 5897f5dcb90..14a38b8cef1 100644
--- a/python/train.py
+++ b/python/train.py
@@ -63,8 +63,8 @@ def show_time():
 
 
 def solve(proto, snapshot, gpus, timing, uid, rank):
-    caffe.set_mode_gpu()
     caffe.set_device(gpus[rank])
+    caffe.set_mode_gpu()
     caffe.set_solver_count(len(gpus))
     caffe.set_solver_rank(rank)
     caffe.set_multiprocess(True)