def _to_batched_tensor_list(self, value): if self._dense_shape.merge_with( tensor_util.constant_value_as_shape( value.dense_shape)).ndims == 0: raise ValueError( "Unbatching a sparse tensor is only supported for rank >= 1") return [ sparse_ops.serialize_many_sparse(value, out_type=dtypes.variant) ]
def benchmarkVeryLarge2DFloatSparseTensor(self): np.random.seed(127) num_elements = 10000 batch_size = 64 indices_batch = np.random.randint(batch_size, size=num_elements, dtype=np.int64) indices_value = np.arange(num_elements, dtype=np.int64) indices = np.asarray(sorted(zip(indices_batch, indices_value)), dtype=np.int64) values = ["feature_value_for_embedding_lookup"] * num_elements shape = np.asarray([batch_size, num_elements], dtype=np.int64) with session.Session(config=benchmark.benchmark_config()) as sess: with ops.device("/cpu:0"): indices = variables.Variable(indices) values = variables.Variable(values) shape = variables.Variable(shape) st = sparse_tensor_lib.SparseTensor(indices, values, shape) st_handles = add_many_sparse_to_tensors_map(st) st_roundtrip = take_many_sparse_from_tensors_map( sparse_map_op=st_handles.op, sparse_handles=st_handles) st_roundtrip_op = st_roundtrip.values.op st_serialized = sparse_ops.serialize_many_sparse(st) st_deserialized = sparse_ops.deserialize_many_sparse( st_serialized, dtype=values.dtype) st_deserialized_op = st_deserialized.values.op variables.global_variables_initializer().run() st_roundtrip_values = self.evaluate(st_roundtrip) st_deserialized_values = self.evaluate(st_deserialized) np.testing.assert_equal(st_roundtrip_values.values, st_deserialized_values.values) np.testing.assert_equal(st_roundtrip_values.indices, st_deserialized_values.indices) np.testing.assert_equal(st_roundtrip_values.dense_shape, st_deserialized_values.dense_shape) self.run_op_benchmark( sess, st_roundtrip_op, min_iters=2000, name="benchmark_very_large_2d_float_st_tensor_maps") self.run_op_benchmark( sess, st_deserialized_op, min_iters=2000, name="benchmark_very_large_2d_float_st_serialization")
def benchmarkVeryLarge2DFloatSparseTensor(self): np.random.seed(127) num_elements = 10000 batch_size = 64 indices_batch = np.random.randint( batch_size, size=num_elements, dtype=np.int64) indices_value = np.arange(num_elements, dtype=np.int64) indices = np.asarray( sorted(zip(indices_batch, indices_value)), dtype=np.int64) values = ["feature_value_for_embedding_lookup"] * num_elements shape = np.asarray([batch_size, num_elements], dtype=np.int64) with session.Session(config=benchmark.benchmark_config()) as sess: with ops.device("/cpu:0"): indices = variables.Variable(indices) values = variables.Variable(values) shape = variables.Variable(shape) st = sparse_tensor_lib.SparseTensor(indices, values, shape) st_handles = add_many_sparse_to_tensors_map(st) st_roundtrip = take_many_sparse_from_tensors_map( sparse_map_op=st_handles.op, sparse_handles=st_handles) st_roundtrip_op = st_roundtrip.values.op st_serialized = sparse_ops.serialize_many_sparse(st) st_deserialized = sparse_ops.deserialize_many_sparse( st_serialized, dtype=values.dtype) st_deserialized_op = st_deserialized.values.op variables.global_variables_initializer().run() st_roundtrip_values = sess.run(st_roundtrip) st_deserialized_values = sess.run(st_deserialized) np.testing.assert_equal(st_roundtrip_values.values, st_deserialized_values.values) np.testing.assert_equal(st_roundtrip_values.indices, st_deserialized_values.indices) np.testing.assert_equal(st_roundtrip_values.dense_shape, st_deserialized_values.dense_shape) self.run_op_benchmark( sess, st_roundtrip_op, min_iters=2000, name="benchmark_very_large_2d_float_st_tensor_maps") self.run_op_benchmark( sess, st_deserialized_op, min_iters=2000, name="benchmark_very_large_2d_float_st_serialization")
def serialize_many_sparse_tensors(tensors): """Serializes many sparse tensors into a batch. Args: tensors: a tensor structure to serialize. Returns: `tensors` with any sparse tensors replaced by the serialized batch. """ ret = nest.pack_sequence_as(tensors, [ sparse_ops.serialize_many_sparse(tensor, out_type=dtypes.variant) if sparse_tensor.is_sparse(tensor) else tensor for tensor in nest.flatten(tensors) ]) return ret
def testSerializeManyDeserializeManyRoundTrip(self): with self.test_session(use_gpu=False) as sess: # N == 4 because shape_value == [4, 5] indices_value = np.array([[0, 0], [0, 1], [2, 0]], dtype=np.int64) values_value = np.array([b"a", b"b", b"c"]) shape_value = np.array([4, 5], dtype=np.int64) sparse_tensor = self._SparseTensorPlaceholder(dtype=dtypes.string) serialized = sparse_ops.serialize_many_sparse(sparse_tensor) deserialized = sparse_ops.deserialize_many_sparse( serialized, dtype=dtypes.string) serialized_value, deserialized_value = sess.run( [serialized, deserialized], feed_dict={ sparse_tensor.indices: indices_value, sparse_tensor.values: values_value, sparse_tensor.dense_shape: shape_value }) self.assertEqual(serialized_value.shape, (4, 3)) self.assertAllEqual(deserialized_value.indices, indices_value) self.assertAllEqual(deserialized_value.values, values_value) self.assertAllEqual(deserialized_value.dense_shape, shape_value)
def _maybe_serialize(t): if not isinstance(t, ops.SparseTensor): return t return (sparse_ops.serialize_many_sparse(t) if enqueue_many else sparse_ops.serialize_sparse(t))
def _maybe_serialize(t, is_sparse): if not is_sparse: return t return (sparse_ops.serialize_many_sparse(t) if enqueue_many else sparse_ops.serialize_sparse(t))
def _to_batched_tensor_list(self, value): if self._dense_shape.merge_with( tensor_util.constant_value_as_shape(value.dense_shape)).ndims == 0: raise ValueError( "Unbatching a sparse tensor is only supported for rank >= 1") return [sparse_ops.serialize_many_sparse(value, out_type=dtypes.variant)]