Make occurence (op run times and op definition) selectable

in all views to address the loop problem.

When a node is in loop, its execution times are accumulated, its run times
will increase.

PiperOrigin-RevId: 159912429

4 files changed, 127 insertions, 12 deletions

diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/BUILD b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/BUILD
index e844046811..7abfb62214 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/BUILD
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/BUILD
@@ -65,6 +65,7 @@ cuda_py_test(
     name = "run_metadata_test",
     srcs = ["run_metadata_test.py"],
     additional_deps = [
+        ":model_analyzer_testlib",
         "//tensorflow/contrib/tfprof/python/tools/tfprof:model_analyzer",
         "//tensorflow/python:array_ops",
         "//tensorflow/python:client_testlib",
@@ -72,6 +73,7 @@ cuda_py_test(
         "//tensorflow/python:random_ops",
         "//tensorflow/tools/tfprof:protos_all_py",
     ],
+    tags = ["no_pip"],
 )
 
 # -----------------------------------------------------------------------------
diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/print_model_analysis_test.py b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/print_model_analysis_test.py
index 091fcdef88..84a37e087b 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/print_model_analysis_test.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/print_model_analysis_test.py
@@ -157,6 +157,9 @@ class PrintModelAnalysisTest(test.TestCase):
             cpu_exec_micros: 0
             total_accelerator_exec_micros: 0
             total_cpu_exec_micros: 0
+            run_count: 0
+            total_run_count: 0
+            total_definition_count: 1
           }
           children {
             name: "DW"
@@ -213,6 +216,9 @@ class PrintModelAnalysisTest(test.TestCase):
               cpu_exec_micros: 0
               total_accelerator_exec_micros: 0
               total_cpu_exec_micros: 0
+              run_count: 0
+              total_run_count: 0
+              total_definition_count: 1
             }
             children {
               name: "DW/Initializer"
@@ -249,6 +255,9 @@ class PrintModelAnalysisTest(test.TestCase):
                   cpu_exec_micros: 0
                   total_accelerator_exec_micros: 0
                   total_cpu_exec_micros: 0
+                  run_count: 0
+                  total_run_count: 0
+                  total_definition_count: 1
                 }
                 children {
                   name: "DW/Initializer/random_normal/mean"
@@ -263,6 +272,9 @@ class PrintModelAnalysisTest(test.TestCase):
                   cpu_exec_micros: 0
                   total_accelerator_exec_micros: 0
                   total_cpu_exec_micros: 0
+                  run_count: 0
+                  total_run_count: 0
+                  total_definition_count: 1
                 }
                 children {
                   name: "DW/Initializer/random_normal/mul"
@@ -302,6 +314,9 @@ class PrintModelAnalysisTest(test.TestCase):
                   cpu_exec_micros: 0
                   total_accelerator_exec_micros: 0
                   total_cpu_exec_micros: 0
+                  run_count: 0
+                  total_run_count: 0
+                  total_definition_count: 1
                 }
                 children {
                   name: "DW/Initializer/random_normal/shape"
@@ -316,6 +331,9 @@ class PrintModelAnalysisTest(test.TestCase):
                   cpu_exec_micros: 0
                   total_accelerator_exec_micros: 0
                   total_cpu_exec_micros: 0
+                  run_count: 0
+                  total_run_count: 0
+                  total_definition_count: 1
                 }
                 children {
                   name: "DW/Initializer/random_normal/stddev"
@@ -330,6 +348,9 @@ class PrintModelAnalysisTest(test.TestCase):
                   cpu_exec_micros: 0
                   total_accelerator_exec_micros: 0
                   total_cpu_exec_micros: 0
+                  run_count: 0
+                  total_run_count: 0
+                  total_definition_count: 1
                 }
                 float_ops: 0
                 total_float_ops: 0
@@ -362,6 +383,9 @@ class PrintModelAnalysisTest(test.TestCase):
                 cpu_exec_micros: 0
                 total_accelerator_exec_micros: 0
                 total_cpu_exec_micros: 0
+                run_count: 0
+                total_run_count: 0
+                total_definition_count: 6
               }
               float_ops: 0
               total_float_ops: 0
@@ -369,6 +393,9 @@ class PrintModelAnalysisTest(test.TestCase):
               cpu_exec_micros: 0
               total_accelerator_exec_micros: 0
               total_cpu_exec_micros: 0
+              run_count: 0
+              total_run_count: 0
+              total_definition_count: 7
             }
             children {
               name: "DW/read"
@@ -400,6 +427,9 @@ class PrintModelAnalysisTest(test.TestCase):
               cpu_exec_micros: 0
               total_accelerator_exec_micros: 0
               total_cpu_exec_micros: 0
+              run_count: 0
+              total_run_count: 0
+              total_definition_count: 1
             }
             float_ops: 0
             total_float_ops: 0
@@ -407,6 +437,9 @@ class PrintModelAnalysisTest(test.TestCase):
             cpu_exec_micros: 0
             total_accelerator_exec_micros: 0
             total_cpu_exec_micros: 0
+            run_count: 0
+            total_run_count: 0
+            total_definition_count: 10
           }
           children {
             name: "zeros"
@@ -421,13 +454,19 @@ class PrintModelAnalysisTest(test.TestCase):
             cpu_exec_micros: 0
             total_accelerator_exec_micros: 0
             total_cpu_exec_micros: 0
+            run_count: 0
+            total_run_count: 0
+            total_definition_count: 1
           }
           float_ops: 0
           total_float_ops: 0
           accelerator_exec_micros: 0
           cpu_exec_micros: 0
           total_accelerator_exec_micros: 0
-          total_cpu_exec_micros: 0""", expected_pb)
+          total_cpu_exec_micros: 0
+          run_count: 0
+          total_run_count: 0
+          total_definition_count: 13""", expected_pb)
       self.assertEqual(expected_pb, tfprof_pb)
 
 
diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/run_metadata_test.py b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/run_metadata_test.py
index feb20dc0f4..9c59df3117 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/internal/run_metadata_test.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/internal/run_metadata_test.py
@@ -27,12 +27,13 @@ from tensorflow.python.client import session
 from tensorflow.python.framework import ops
 from tensorflow.python.ops import math_ops
 from tensorflow.python.ops import random_ops
+from tensorflow.python.ops import variables
 from tensorflow.python.platform import test
 
 # pylint: disable=g-bad-import-order
 # XXX: this depends on pywrap_tensorflow and must come later
 from tensorflow.contrib.tfprof.python.tools.tfprof import model_analyzer
-
+from tensorflow.contrib.tfprof.python.tools.tfprof.internal import model_analyzer_testlib as lib
 SIZE = 1300
 
 
@@ -68,15 +69,32 @@ def _run_model():
     return tfprof_node, run_metadata
 
 
+def _run_loop_model():
+  with session.Session() as sess:
+    x = lib.BuildFullModel()
+
+    sess.run(variables.global_variables_initializer())
+    run_meta = config_pb2.RunMetadata()
+    _ = sess.run(x,
+                 options=config_pb2.RunOptions(
+                     trace_level=config_pb2.RunOptions.FULL_TRACE),
+                 run_metadata=run_meta)
+
+    tfprof_node = model_analyzer.print_model_analysis(
+        sess.graph, run_meta,
+        tfprof_options=model_analyzer.PRINT_ALL_TIMING_MEMORY)
+    return tfprof_node, run_meta
+
+
 class RunMetadataTest(test.TestCase):
 
   def testGPU(self):
     if not test.is_gpu_available():
       return
 
+    ops.reset_default_graph()
     with ops.device('/gpu:0'):
       tfprof_node, run_meta = _run_model()
-
       self.assertEqual(tfprof_node.children[0].name, 'MatMul')
       self.assertGreater(tfprof_node.children[0].exec_micros, 10)
 
@@ -94,9 +112,9 @@ class RunMetadataTest(test.TestCase):
     self.assertTrue(has_all_stream)
 
   def testCPU(self):
+    ops.reset_default_graph()
     with ops.device('/cpu:0'):
       tfprof_node, run_meta = _run_model()
-
       self.assertEqual(tfprof_node.children[0].name, 'MatMul')
       self.assertGreater(tfprof_node.children[0].exec_micros, 10)
 
@@ -107,5 +125,61 @@ class RunMetadataTest(test.TestCase):
     ret = _extract_node(run_meta, 'MatMul:MatMul')
     self.assertEqual(len(ret), 0)
 
+  def testLoopCPU(self):
+    ops.reset_default_graph()
+    with ops.device('/cpu:0'):
+      tfprof_node, run_meta = _run_loop_model()
+      # The while-loop caused a node to appear 4 times in scheduling.
+      ret = _extract_node(run_meta,
+                          'rnn/while/rnn/basic_rnn_cell/basic_rnn_cell/MatMul')
+      self.assertEqual(len(ret['/job:localhost/replica:0/task:0/cpu:0']), 4)
+
+      total_cpu_execs = 0
+      for node in ret['/job:localhost/replica:0/task:0/cpu:0']:
+        total_cpu_execs += node.op_end_rel_micros
+
+      mm_node = lib.SearchTFProfNode(
+          tfprof_node,
+          'rnn/while/rnn/basic_rnn_cell/basic_rnn_cell/MatMul')
+
+      self.assertEqual(mm_node.run_count, 4)
+      self.assertEqual(mm_node.cpu_exec_micros, total_cpu_execs)
+      self.assertEqual(mm_node.exec_micros, total_cpu_execs)
+
+  def testLoopGPU(self):
+    if not test.is_gpu_available():
+      return
+
+    ops.reset_default_graph()
+    with ops.device('/gpu:0'):
+      tfprof_node, run_meta = _run_loop_model()
+      # The while-loop caused a node to appear 4 times in scheduling.
+      ret = _extract_node(run_meta,
+                          'rnn/while/rnn/basic_rnn_cell/basic_rnn_cell/MatMul')
+      self.assertEqual(len(ret['/job:localhost/replica:0/task:0/gpu:0']), 4)
+
+      total_cpu_execs = 0
+      for node in ret['/job:localhost/replica:0/task:0/gpu:0']:
+        total_cpu_execs += node.op_end_rel_micros
+
+      ret = _extract_node(
+          run_meta,
+          'rnn/while/rnn/basic_rnn_cell/basic_rnn_cell/MatMul:MatMul')
+      self.assertGreaterEqual(len(ret['/gpu:0/stream:all']), 4)
+
+      total_accelerator_execs = 0
+      for node in ret['/gpu:0/stream:all']:
+        total_accelerator_execs += node.op_end_rel_micros
+
+      mm_node = lib.SearchTFProfNode(
+          tfprof_node,
+          'rnn/while/rnn/basic_rnn_cell/basic_rnn_cell/MatMul')
+
+      self.assertEqual(mm_node.run_count, 4)
+      self.assertEqual(mm_node.accelerator_exec_micros, total_accelerator_execs)
+      self.assertEqual(mm_node.cpu_exec_micros, total_cpu_execs)
+      self.assertEqual(mm_node.exec_micros,
+                       total_cpu_execs + total_accelerator_execs)
+
 if __name__ == '__main__':
   test.main()
diff --git a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
index ec7540a657..fea27a82a5 100644
--- a/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
+++ b/tensorflow/contrib/tfprof/python/tools/tfprof/model_analyzer_test.py
@@ -34,7 +34,7 @@ class PrintModelAnalysisTest(test.TestCase):
 
   def testDumpToFile(self):
     ops.reset_default_graph()
-    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS
+    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
     outfile = os.path.join(test.get_temp_dir(), 'dump')
     opts['output'] = 'file:outfile=' + outfile
 
@@ -52,7 +52,7 @@ class PrintModelAnalysisTest(test.TestCase):
 
   def testSelectEverything(self):
     ops.reset_default_graph()
-    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS
+    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
     outfile = os.path.join(test.get_temp_dir(), 'dump')
     opts['output'] = 'file:outfile=' + outfile
     opts['account_type_regexes'] = ['.*']
@@ -77,7 +77,7 @@ class PrintModelAnalysisTest(test.TestCase):
       with gfile.Open(outfile, 'r') as f:
         # pylint: disable=line-too-long
         self.assertEqual(
-            'node name | # parameters | # float_ops | assigned devices | op types | input shapes\n_TFProfRoot (--/451 params, --/10.44k flops, _kTFScopeParent, )\n  Conv2D (0/0 params, 5.83k/5.83k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 0:2x6x6x3|1:3x3x3x6)\n  Conv2D_1 (0/0 params, 4.61k/4.61k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 0:2x3x3x6|1:2x2x6x12)\n  DW (3x3x3x6, 162/162 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, )\n    DW/Assign (0/0 params, 0/0 flops, Assign, 0:3x3x3x6|1:3x3x3x6)\n    DW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, )\n      DW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0:3x3x3x6|1:1)\n        DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0:4)\n        DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, )\n        DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0:3x3x3x6|1:1)\n        DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, )\n        DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, )\n    DW/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 0:3x3x3x6)\n  DW2 (2x2x6x12, 288/288 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, )\n    DW2/Assign (0/0 params, 0/0 flops, Assign, 0:2x2x6x12|1:2x2x6x12)\n    DW2/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, )\n      DW2/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0:2x2x6x12|1:1)\n        DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0:4)\n        DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, )\n        DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0:2x2x6x12|1:1)\n        DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, )\n        DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, )\n    DW2/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 0:2x2x6x12)\n  ScalarW (1, 1/1 params, 0/0 flops, VariableV2|_trainable_variables, )\n    ScalarW/Assign (0/0 params, 0/0 flops, Assign, 0:1|1:1)\n    ScalarW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, )\n      ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0:1|1:1)\n        ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0:0)\n        ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, )\n        ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0:1|1:1)\n        ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, )\n        ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, )\n    ScalarW/read (0/0 params, 0/0 flops, Identity, 0:1)\n  init (0/0 params, 0/0 flops, NoOp, 0:1|1:3x3x3x6|2:2x2x6x12)\n  zeros (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const, )\n',
+            'node name | # parameters | # float_ops | assigned devices | op types | op count (run|defined) | input shapes\n_TFProfRoot (--/451 params, --/10.44k flops, _kTFScopeParent, --/7|--/35, )\n  Conv2D (0/0 params, 5.83k/5.83k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x6x6x3|1:3x3x3x6)\n  Conv2D_1 (0/0 params, 4.61k/4.61k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x3x3x6|1:2x2x6x12)\n  DW (3x3x3x6, 162/162 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n    DW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:3x3x3x6|1:3x3x3x6)\n    DW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n      DW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:3x3x3x6|1:1)\n        DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n        DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:3x3x3x6|1:1)\n        DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n    DW/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:3x3x3x6)\n  DW2 (2x2x6x12, 288/288 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n    DW2/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:2x2x6x12|1:2x2x6x12)\n    DW2/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n      DW2/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:2x2x6x12|1:1)\n        DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n        DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:2x2x6x12|1:1)\n        DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n    DW2/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:2x2x6x12)\n  ScalarW (1, 1/1 params, 0/0 flops, VariableV2|_trainable_variables, 0/0|1/10, )\n    ScalarW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:1|1:1)\n    ScalarW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n      ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:1|1:1)\n        ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:0)\n        ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:1|1:1)\n        ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n        ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n    ScalarW/read (0/0 params, 0/0 flops, Identity, 0/0|1/1, 0:1)\n  init (0/0 params, 0/0 flops, NoOp, 0/0|1/1, 0:1|1:3x3x3x6|2:2x2x6x12)\n  zeros (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const, 1/1|1/1, )\n',
             f.read())
         # pylint: enable=line-too-long
 
@@ -143,12 +143,12 @@ class PrintModelAnalysisTest(test.TestCase):
       with gfile.Open(outfile, 'r') as f:
         lines = f.read().split('\n')
         result = '\n'.join([l[:min(len(l), 80)] for l in lines])
-        self.assertEqual('node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/54.08k flops)\n  model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (0/1.80k para\n    model_analyzer_testlib.py:35:BuildSmallModel:image = array_ops... (0/0 param\n    model_analyzer_testlib.py:39:BuildSmallModel:initializer=init_... (0/4 param\n    model_analyzer_testlib.py:43:BuildSmallModel:initializer=init_... (0/648 par\n    model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n    model_analyzer_testlib.py:48:BuildSmallModel:initializer=init_... (0/1.15k p\n    model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n  model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (0/1.04k para\n  model_analyzer_testlib.py:64:BuildFullModel:target = array_op... (0/0 params, \n  model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (0/0 params, \n  model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min... (0/0 params, \n',
+        self.assertEqual('node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/91.04k flops)\n  model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (0/1.80k para\n    model_analyzer_testlib.py:35:BuildSmallModel:image = array_ops... (0/0 param\n    model_analyzer_testlib.py:39:BuildSmallModel:initializer=init_... (0/4 param\n    model_analyzer_testlib.py:43:BuildSmallModel:initializer=init_... (0/648 par\n    model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n    model_analyzer_testlib.py:48:BuildSmallModel:initializer=init_... (0/1.15k p\n    model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n  model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (0/1.04k para\n  model_analyzer_testlib.py:64:BuildFullModel:target = array_op... (0/0 params, \n  model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (0/0 params, \n  model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min... (0/0 params, \n',
                          result)
 
       self.assertLess(0, tfprof_node.total_exec_micros)
       self.assertEqual(2844, tfprof_node.total_parameters)
-      self.assertEqual(54080, tfprof_node.total_float_ops)
+      self.assertEqual(91040, tfprof_node.total_float_ops)
       self.assertEqual(5, len(tfprof_node.children))
       self.assertEqual('_TFProfRoot', tfprof_node.name)
       self.assertEqual(
@@ -226,7 +226,7 @@ class PrintModelAnalysisTest(test.TestCase):
 
   def testOpView(self):
     ops.reset_default_graph()
-    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS
+    opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
     outfile = os.path.join(test.get_temp_dir(), 'dump')
     opts['output'] = 'file:outfile=' + outfile
     opts['account_type_regexes'] = ['.*']
@@ -250,8 +250,8 @@ class PrintModelAnalysisTest(test.TestCase):
       with gfile.Open(outfile, 'r') as f:
         # pylint: disable=line-too-long
         self.assertEqual(
-            'nodename|totalexecutiontime|acceleratorexecutiontime|cpuexecutiontime|#parameters|opoccurrence|input',
-            f.read().replace('\t', '').replace(' ', '')[0:100])
+            'nodename|totalexecutiontime|acceleratorexecutiontime|cpuexecutiontime|#parameters|opoccurrence(run|defined)|inputshapes\n',
+            f.read().replace('\t', '').replace(' ', '')[0:120])
         # pylint: enable=line-too-long
 
       total_children = 0