Mutablehashtable lookup support full size dynamic default values.

This PR is one part of RFC:tensorflow/community#237

Author: rhdong

tensorflow/core/framework/lookup_interface.cc

@@ -83,10 +83,17 @@ Status LookupInterface::CheckFindArguments(const Tensor& key,
                                            const Tensor& default_value) {
   TF_RETURN_IF_ERROR(CheckKeyAndValueTypes(key, default_value));
   TF_RETURN_IF_ERROR(CheckKeyShape(key.shape()));
-  if (default_value.shape() != value_shape()) {
+  TensorShape fullsize_value_shape = key.shape();
+  for (int i = 0; i < key_shape().dims(); ++i) {
+    fullsize_value_shape.RemoveDim(fullsize_value_shape.dims() - 1);
+  }
+  fullsize_value_shape.AppendShape(value_shape());
+  if (default_value.shape() != value_shape() &&
+      default_value.shape() != fullsize_value_shape) {
     return errors::InvalidArgument(
-        "Expected shape ", value_shape().DebugString(),
-        " for default value, got ", default_value.shape().DebugString());
+        "Expected shape ", value_shape().DebugString(), " or ",
+        fullsize_value_shape.DebugString(), " for default value, got ",
+        default_value.shape().DebugString());
   }
   return Status::OK();
 }

tensorflow/core/framework/lookup_interface.h

@@ -128,7 +128,8 @@ class LookupInterface : public ResourceBase {
   // requirements are satisfied, otherwise it returns InvalidArgument:
   // - DataType of the tensor keys equals to the table key_dtype
   // - DataType of the tensor default_value equals to the table value_dtype
-  // - the default_value tensor shape matches the table's value shape.
+  // - the default_value tensor has the required shape given keys and the 
+  //   tables's value shape.
   Status CheckFindArguments(const Tensor& keys, const Tensor& default_value);
 
   string DebugString() const override {

tensorflow/core/kernels/lookup_table_op.cc

@@ -62,13 +62,19 @@ class MutableHashTableOfScalars final : public LookupInterface {
 
     int64 total = value_values.size();
     int64 default_total = default_flat.size();
-    bool is_full_default = (total == default_total);
+    bool is_full_size_default = (total == default_total);
 
     tf_shared_lock l(mu_);
     for (int64 i = 0; i < key_values.size(); ++i) {
+      // is_full_size_default is true: 
+      //   Each key has an independent default value, key_values(i) 
+      //   corresponding uses default_flat(i) as its default value.
+      // 
+      // is_full_size_default is false: 
+      //   All keys will share the default_flat(0) as default value.
       value_values(i) = gtl::FindWithDefault(
           table_, SubtleMustCopyIfIntegral(key_values(i)),
-          is_full_default ? default_flat(i) : default_flat(0));
+          is_full_size_default ? default_flat(i) : default_flat(0));
     }
 
     return Status::OK();
@@ -185,7 +191,7 @@ class MutableHashTableOfTensors final : public LookupInterface {
 
     int64 total = value_values.size();
     int64 default_total = default_flat.size();
-    bool is_full_default = (total == default_total);
+    bool is_full_size_default = (total == default_total);
 
     tf_shared_lock l(mu_);
     for (int64 i = 0; i < key_values.size(); ++i) {
@@ -196,9 +202,15 @@ class MutableHashTableOfTensors final : public LookupInterface {
           value_values(i, j) = value_vec->at(j);
         }
       } else {
+        // is_full_size_default is true: 
+        //   Each key has an independent default value, key_values(i) 
+        //   corresponding uses default_flat(i) as its default value.
+        //
+        // is_full_size_default is false: 
+        //   All keys will share the default_flat(0) as default value.
         for (int64 j = 0; j < value_dim; j++) {
           value_values(i, j) =
-              is_full_default ? default_flat(i, j) : default_flat(0, j);
+              is_full_size_default ? default_flat(i, j) : default_flat(0, j);
         }
       }
     }

tensorflow/python/kernel_tests/lookup_ops_test.py

@@ -3309,6 +3309,71 @@ def testMutableHashTableFindHighRank(self):
       result = self.evaluate(output)
       self.assertAllEqual([[0, 1], [-1, -1]], result)
 
+  def testMutableHashTableFindWithInvalidShapeDefaultValue(self):
+    default_val = [-1, -1]
+    table = lookup_ops.MutableHashTable(dtypes.string, dtypes.int64,
+                                        default_val)
+
+    input_string = constant_op.constant([["brain", "salad"],
+                                         ["tank", "tarkus"]])
+
+    invalid_default_val = constant_op.constant(
+        [[-2, -3], [-4, -5], [-6, -7], [-8, -9]], dtypes.int64)
+
+    with self.assertRaisesRegex(
+        (ValueError, errors_impl.InvalidArgumentError),
+        "Expected shape \[2\] or \[2,2,2\] for default value, got \[4,2]"):
+      self.evaluate(table.lookup(input_string, invalid_default_val))
+
+    invalid_default_val = constant_op.constant([[[-2, -3], [-4, -5]]],
+                                               dtypes.int64)
+    with self.assertRaisesRegex(
+        (ValueError, errors_impl.InvalidArgumentError),
+        "Expected shape \[2\] or \[2,2,2\] for default value, got \[1,2,2\]"):
+      self.evaluate(table.lookup(input_string, invalid_default_val))
+
+  def testMutableHashTableFindHighRankScalarWithDynamicDefaultValue(self):
+    default_val = -1
+    keys = constant_op.constant(["brain", "salad", "surgery"])
+    values = constant_op.constant([0, 1, 2], dtypes.int64)
+    table = lookup_ops.MutableHashTable(dtypes.string, dtypes.int64,
+                                        default_val)
+
+    self.evaluate(table.insert(keys, values))
+    self.assertAllEqual(3, self.evaluate(table.size()))
+
+    input_string = constant_op.constant([["brain", "salad"],
+                                         ["tank", "tarkus"]])
+
+    dynamic_default_val = constant_op.constant([[-2, -3], [-4, -5]],
+                                               dtypes.int64)
+    output = table.lookup(input_string, dynamic_default_val)
+    self.assertAllEqual([2, 2], output.get_shape())
+
+    result = self.evaluate(output)
+    self.assertAllEqual([[0, 1], [-4, -5]], result)
+
+  def testMutableHashTableFindHighRankVectorWithDynamicDefaultValue(self):
+    default_val = [-1, -1]
+    keys = constant_op.constant(["brain", "salad", "surgery"])
+    values = constant_op.constant([[0, 1], [2, 3], [4, 5]], dtypes.int64)
+    table = lookup_ops.MutableHashTable(dtypes.string, dtypes.int64,
+                                        default_val)
+
+    self.evaluate(table.insert(keys, values))
+    self.assertAllEqual(3, self.evaluate(table.size()))
+
+    input_string = constant_op.constant([["brain", "salad"],
+                                         ["tank", "tarkus"]])
+
+    dynamic_default_val = constant_op.constant(
+        [[[-2, -3], [-4, -5]], [[-6, -7], [-8, -9]]], dtypes.int64)
+    output = table.lookup(input_string, dynamic_default_val)
+    self.assertAllEqual([2, 2, 2], output.get_shape())
+
+    result = self.evaluate(output)
+    self.assertAllEqual([[[0, 1], [2, 3]], [[-6, -7], [-8, -9]]], result)
+
   def testMutableHashTableInsertHighRank(self):
     with self.cached_session():
       default_val = -1

tensorflow/python/ops/lookup_ops.py

@@ -1819,8 +1819,22 @@ def lookup(self, keys, dynamic_default_values=None, name=None):
       keys: Keys to look up. Can be a tensor of any shape. Must match the
         table's key_dtype.
       dynamic_default_values: The values to use if a key is missing in the
-        table. If None (by default), the static default_value
-        `self._default_value` will be used.
+        table. If None (by default), the `table.default_value` will be used.
+        Shape of `dynamic_default_values` must be same with
+        `table.default_value` or the lookup result tensor.
+        In the latter case, each key will have a different default value.
+
+        For example:
+
+          ```python
+          keys = [0, 1, 3]
+          dynamic_default_values = [[1, 3, 4], [2, 3, 9], [8, 3, 0]]
+
+          # The key '0' will use [1, 3, 4] as default value.
+          # The key '1' will use [2, 3, 9] as default value.
+          # The key '3' will use [8, 3, 0] as default value.
+          ```
+
       name: A name for the operation (optional).
 
     Returns: