Port new added files to Python3

python/paddle/fluid/contrib/memory_usage_calc.py

@@ -20,6 +20,8 @@ batch size to fully utilize a GPU.
 This API is still under active development and may change drastically.
 """
 
+import six
+
 from .. import core
 from ..framework import Program, Variable
 
@@ -72,7 +74,7 @@ def memory_usage(program, batch_size):
 
     # Get the var_name list of first block and calculate
     total_memory = 0.0
-    for var in program.global_block().vars.itervalues():
+    for var in six.itervalues(program.global_block().vars):
         data_count = 1
         for x in var.shape:
             if x == -1:
@@ -81,10 +83,10 @@ def memory_usage(program, batch_size):
                 data_count *= x
         var_memory = data_count * dtype_to_size[var.dtype]
         if DEBUG:
-            print "%s memory usage: %d" % (var.name, var_memory)
+            print("%s memory usage: %d" % (var.name, var_memory))
         total_memory += var_memory
     if DEBUG:
-        print "total memory usage: %.2f" % (total_memory)
+        print("total memory usage: %.2f" % (total_memory))
 
     # Convert appropriate unit
     unit_str = "B"

python/paddle/fluid/tests/unittests/dist_transformer.py

@@ -160,6 +160,7 @@ def get_model():
     avg_cost = transformer(use_feed=False)
     optimizer = fluid.optimizer.Adam()
     optimizer.minimize(avg_cost)
+    fluid.memory_optimize(fluid.default_main_program())
     return avg_cost