Make python unit test of beam_search_op and beam_searc_decode_op run correctly

paddle/fluid/operators/beam_search_decode_op_test.cc

@@ -76,7 +76,7 @@ void GenerateExample(const std::vector<size_t>& level_0,
 TEST(BeamSearchDecodeOp, Backtrace) {
   CPUPlace place;
 
-  // we will constuct a sample data with 4 steps and 2 source sentences
+  // Construct sample data with 5 steps and 2 source sentences
   // beam_size = 2, start_id = 0, end_id = 1
   LoDTensorArray ids;
   LoDTensorArray scores;

paddle/fluid/operators/beam_search_op_test.cc

@@ -67,7 +67,7 @@ TEST(beam_search_op, run) {
   LoDTensor pre_scores;
   pre_scores.Resize(framework::make_ddim(vector<int64_t>(4, 1)));
   for (int i = 0; i < 4; i++) {
-    pre_scores.mutable_data<float>(place)[i] = 0.1;
+    pre_scores.mutable_data<float>(place)[i] = 0.1 * (i + 1);
   }
 
   BeamSearch beamsearch(ids, scores, (size_t)0, (size_t)2, 0);

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

@@ -32,32 +32,44 @@ class TestBeamSearchDecodeOp(unittest.TestCase):
 
     def test_get_set(self):
         ids = self.scope.var("ids").get_lod_tensor_array()
-        self.append_lod_tensor(
-            ids, [[0, 3, 6], [0, 1, 2, 3, 4, 5, 6]],
-            np.array(
-                [1, 2, 3, 4, 5, 6], dtype="int64"))
-        self.append_lod_tensor(
-            ids, [[0, 3, 6], [0, 1, 1, 3, 5, 5, 6]],
-            np.array(
-                [0, 1, 2, 3, 4, 5], dtype="int64"))
-        self.append_lod_tensor(
-            ids, [[0, 3, 6], [0, 0, 1, 2, 3, 4, 5]],
-            np.array(
-                [0, 1, 2, 3, 4], dtype="int64"))
-
         scores = self.scope.var("scores").get_lod_tensor_array()
-        self.append_lod_tensor(
-            scores, [[0, 3, 6], [0, 1, 2, 3, 4, 5, 6]],
-            np.array(
-                [1, 2, 3, 4, 5, 6], dtype="float64"))
-        self.append_lod_tensor(
-            scores, [[0, 3, 6], [0, 1, 1, 3, 5, 5, 6]],
-            np.array(
-                [0, 1, 2, 3, 4, 5], dtype="float64"))
-        self.append_lod_tensor(
-            scores, [[0, 3, 6], [0, 0, 1, 2, 3, 4, 5]],
-            np.array(
-                [0, 1, 2, 3, 4], dtype="float64"))
+        # Construct sample data with 5 steps and 2 source sentences
+        # beam_size = 2, end_id = 1
+        # start with start_id
+        [
+            self.append_lod_tensor(
+                array, [[0, 1, 2], [0, 1, 2]], np.array(
+                    [0, 0], dtype=dtype))
+            for array, dtype in ((ids, "int64"), (scores, "float32"))
+        ]
+        [
+            self.append_lod_tensor(
+                array, [[0, 1, 2], [0, 2, 4]],
+                np.array(
+                    [2, 3, 4, 5], dtype=dtype))
+            for array, dtype in ((ids, "int64"), (scores, "float32"))
+        ]
+        [
+            self.append_lod_tensor(
+                array, [[0, 2, 4], [0, 2, 2, 4, 4]],
+                np.array(
+                    [3, 1, 5, 4], dtype=dtype))
+            for array, dtype in ((ids, "int64"), (scores, "float32"))
+        ]
+        [
+            self.append_lod_tensor(
+                array, [[0, 2, 4], [0, 1, 2, 3, 4]],
+                np.array(
+                    [1, 1, 3, 5], dtype=dtype))
+            for array, dtype in ((ids, "int64"), (scores, "float32"))
+        ]
+        [
+            self.append_lod_tensor(
+                array, [[0, 2, 4], [0, 0, 0, 2, 2]],
+                np.array(
+                    [5, 1], dtype=dtype))
+            for array, dtype in ((ids, "int64"), (scores, "float32"))
+        ]
 
         sentence_ids = self.scope.var("sentence_ids").get_tensor()
         sentence_scores = self.scope.var("sentence_scores").get_tensor()
@@ -69,16 +81,18 @@ class TestBeamSearchDecodeOp(unittest.TestCase):
             Scores="scores",
             # outputs
             SentenceIds="sentence_ids",
-            SentenceScores="sentence_scores")
+            SentenceScores="sentence_scores",
+            beam_size=2,
+            end_id=1, )
 
         beam_search_decode_op.run(self.scope, self.place)
 
-        expected_lod = [[0, 4, 8], [0, 1, 3, 6, 9, 10, 13, 16, 19]]
+        expected_lod = [[0, 2, 4], [0, 4, 7, 12, 17]]
         self.assertEqual(sentence_ids.lod(), expected_lod)
         self.assertEqual(sentence_scores.lod(), expected_lod)
 
         expected_data = np.array(
-            [2, 1, 0, 3, 1, 0, 3, 2, 1, 5, 4, 3, 2, 4, 4, 3, 6, 5, 4], "int64")
+            [0, 2, 3, 1, 0, 2, 1, 0, 4, 5, 3, 5, 0, 4, 5, 3, 1], "int64")
         self.assertTrue(np.array_equal(np.array(sentence_ids), expected_data))
         self.assertTrue(
             np.array_equal(np.array(sentence_scores), expected_data))

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

@@ -29,6 +29,7 @@ class BeamSearchOpTester(unittest.TestCase):
     def setUp(self):
         self.scope = core.Scope()
         self._create_ids()
+        self._create_pre_scores()
         self._create_scores()
         self._create_pre_ids()
         self.scope.var('selected_ids')
@@ -37,7 +38,8 @@ class BeamSearchOpTester(unittest.TestCase):
     def test_run(self):
         op = Operator(
             'beam_search',
-            pre_ids="pre_ids",
+            pre_ids='pre_ids',
+            pre_scores='pre_scores',
             ids='ids',
             scores='scores',
             selected_ids='selected_ids',
@@ -47,15 +49,27 @@ class BeamSearchOpTester(unittest.TestCase):
             end_id=0, )
         op.run(self.scope, core.CPUPlace())
         selected_ids = self.scope.find_var("selected_ids").get_tensor()
-        print 'selected_ids', np.array(selected_ids)
-        print 'lod', selected_ids.lod()
+        selected_scores = self.scope.find_var("selected_scores").get_tensor()
+        self.assertTrue(
+            np.allclose(
+                np.array(selected_ids), np.array([4, 2, 3, 8])[:, np.newaxis]))
+        self.assertTrue(
+            np.allclose(
+                np.array(selected_scores),
+                np.array([0.5, 0.6, 0.9, 0.7])[:, np.newaxis]))
+        self.assertEqual(selected_ids.lod(),
+                         [[0L, 2L, 4L], [0L, 1L, 2L, 3L, 4L]])
 
     def _create_pre_ids(self):
         np_data = np.array([[1, 2, 3, 4]], dtype='int64')
-        tensor = create_tensor(self.scope, "pre_ids", np_data)
+        tensor = create_tensor(self.scope, 'pre_ids', np_data)
+
+    def _create_pre_scores(self):
+        np_data = np.array([[0.1, 0.2, 0.3, 0.4]], dtype='float32')
+        tensor = create_tensor(self.scope, 'pre_scores', np_data)
 
     def _create_ids(self):
-        self.lod = [[0, 1, 4], [0, 1, 2, 3, 4]]
+        self.lod = [[0, 2, 4], [0, 1, 2, 3, 4]]
         np_data = np.array(
             [[4, 2, 5], [2, 1, 3], [3, 5, 2], [8, 2, 1]], dtype='int64')
         tensor = create_tensor(self.scope, "ids", np_data)