def test_update_embedding_param(self): params = Parameters() for name in ["test_1", "test_2"]: params.embedding_params[name] = EmbeddingTable(name, 8) slot_key = get_slot_table_name(name, "momentum") params.embedding_params[slot_key] = EmbeddingTable( slot_key, 8, "0.0", True) indices = { "test_1": np.array([1, 5]), "test_2": np.array([10]), } embed_vars = { "test_1": tf.Variable(np.random.rand(2, 8).astype(np.float32)), "test_2": tf.Variable(np.random.rand(1, 8).astype(np.float32)), } slot_vars = { "test_1": { "momentum": tf.Variable(np.random.rand(2, 8).astype(np.float32)) }, "test_2": { "momentum": tf.Variable(np.random.rand(1, 8).astype(np.float32)) }, } opt = SGD(momentum=0.1) opt_wrapper = OptimizerWrapper(opt, None, None, params.set_embedding_param) opt_wrapper._tls._unique_ids_all_layers = indices opt_wrapper._tls._embed_variables = embed_vars opt_wrapper._tls._slot_variables = slot_vars opt_wrapper._update_embedding_param() for name in ["test_1", "test_2"]: self.assertTrue( np.allclose( embed_vars[name].numpy(), params.get_embedding_param(name, indices[name]), )) slot = "momentum" slot_table_name = get_slot_table_name(name, slot) self.assertTrue( np.allclose( slot_vars[name][slot].numpy(), params.get_embedding_param(slot_table_name, indices[name]), ))
def _test_correctness(self, optimizer_class, X, Y, seed, **opt_kwargs): """Test the correctness of specific TensorFlow optimizer.""" _model_file = get_module_file_path( os.path.dirname(os.path.realpath(__file__)), "embedding_test_module.KerasEmbeddingModel", ) model_module = load_module(_model_file).__dict__ # train model with TensorFlow optimizer dim = 4 weights = self._random_init_model_weight([(4, dim), (4, dim), (72, 1), (1, )], seed) loss_fn = model_module["loss"] model1 = model_module["KerasEmbeddingModel"](4, dim, weights) opt1 = optimizer_class(**opt_kwargs) _train(model1, opt1, X, Y, loss_fn, random_seed=seed) model2 = model_module["EdlEmbeddingModel"](dim, weights[2:]) opt2 = optimizer_class(**opt_kwargs) embedding_weight_names = [ layer.embedding_weight_name for layer in find_layer(model2, Embedding) ] # create Parameters object and initialize embedding vectors params = Parameters() for weight_name, embed_value in zip(embedding_weight_names, weights[:2]): embed_table = EmbeddingTable(weight_name, dim) embed_table.set(range(len(embed_value)), embed_value) params.embedding_params[weight_name] = embed_table _train_edl_embedding_with_optimizer_wrapper(model2, opt2, X, Y, loss_fn, params, random_seed=seed) # compare trained parameters wrong_msg = ( "The updated parameters of Optimizer Wrapper and TensorFlow " "optimizer %s differ." % opt1.get_config()["name"]) for layer1, layer2 in zip(model1.layers, model2.layers): if "embedding" in layer2.name: w1 = layer1.weights[0].numpy() w2 = params.get_embedding_param(layer2.embedding_weight_name, range(4)) self.assertTrue(np.isclose(w1, w2).all(), msg=wrong_msg) else: for w1, w2 in zip(layer1.weights, layer2.weights): self.assertTrue(np.isclose(w1.numpy(), w2.numpy()).all(), msg=wrong_msg)
def _test_async_correctness( self, grads_and_vars_batches, embed_values, expected_non_embed_values, expected_embed_values=None, ): """Checks the correctness of async OptimizerWrapper. This function creates many threads and these threads call `OptimizerWrapper.apply_gradients` simultaneously. Args: grads_and_vars_batches: A python list of `grads_and_vars`. Every thread takes a `grads_and_vars` and calls `apply_gradients`. embed_values: A python dictionary of `(layer_name, embedding table)`. expected_non_embed_values: A python list of expected non-embdding values after applying gradients. expected_embed_values: A python dictionary of expected embedding values after applying gradients. None means no need to check embedding values. """ thread_num = len(grads_and_vars_batches) input_dims = {} embed_var_n = len(embed_values) params = Parameters() for layer, values in embed_values.items(): embed_dim = values.shape[1] input_dims[layer] = values.shape[0] embed_table = EmbeddingTable(layer, embed_dim) embed_table.set(range(input_dims[layer]), values) params.embedding_params[layer] = embed_table opt = SGD(0.1) opt_wrapper = OptimizerWrapper( opt, True, lookup_embedding_func=params.get_embedding_param, update_embedding_func=params.set_embedding_param, ) # call optimizer_wrapper.apply_gradients asynchronously def _apply_gradients(opt_wrapper, grads_and_vars): # sleep 1s to wait that all threads are in this method call time.sleep(1) opt_wrapper.apply_gradients(grads_and_vars) executor = ThreadPoolExecutor(max_workers=thread_num) tasks = [ executor.submit(_apply_gradients, opt_wrapper, grads_and_vars) for grads_and_vars in grads_and_vars_batches ] _ = [task.result() for task in tasks] # check updated results of non-embedding variables non_embed_vars = [ var for grad, var in grads_and_vars_batches[0][:-embed_var_n] ] for var, expected_value in zip(non_embed_vars, expected_non_embed_values): self.assertTrue(np.isclose(var.numpy(), expected_value).all()) # `expected_embed_values=None` means that no need to check # embedding table if not expected_embed_values: return # check updated results of embedding table for layer, expected_values in expected_embed_values.items(): value = params.get_embedding_param(layer, range(input_dims[layer])) self.assertTrue( any([ np.isclose(value, expected).all() for expected in expected_values ]))
class ParametersTest(unittest.TestCase): def setUp(self): self.params = Parameters() self.model_pb = Model() self.infos_pb = self.model_pb.embedding_table_infos self.tensors_pb = self.model_pb.dense_parameters self.embedding_tables_pb = self.model_pb.embedding_tables self.embedding_table_name = "embedding_1" self.embedding_dim = 10 embedding_pb = self.infos_pb.add() embedding_pb.name = self.embedding_table_name embedding_pb.dim = self.embedding_dim embedding_pb.initializer = "uniform" arr1 = np.random.uniform(size=(3, 4)) serialize_ndarray(arr1, self.tensors_pb["x"]) arr2 = np.random.uniform(size=(4, 5)) serialize_ndarray(arr2, self.tensors_pb["y"]) embedding_vectors = np.random.uniform(size=(2, 10)) embedding_indices = np.array([0, 8]) serialize_indexed_slices( Tensor(None, embedding_vectors, embedding_indices), self.embedding_tables_pb[self.embedding_table_name], ) def _test_get_embedding_param(self, slot_names=[], slot_init_value={}): indices = [0, 3, 7] res = self.params.get_embedding_param( self.embedding_table_name, indices ) self.assertTupleEqual(res.shape, (3, 10)) for slot in slot_names: res = self.params.get_embedding_param( get_slot_table_name(self.embedding_table_name, slot), indices ) self.assertTrue(((res - slot_init_value[slot]) < 0.0001).all()) res = self.params.get_embedding_param(self.embedding_table_name, []) self.assertIsNone(res) with self.assertRaises(ValueError): self.params.get_embedding_param("tom", indices) def test_init_from_model_pb(self): self.params.reset() self.params.init_from_model_pb(self.model_pb) res = self.params.non_embedding_params self.assertTrue("x" in res) self.assertTrue("y" in res) self.assertTrue(res["x"].trainable) self.assertTupleEqual(tuple(res["y"].shape.as_list()), (4, 5)) self._test_get_embedding_param() def test_non_embedding_params(self): self.params.reset() res = self.params.non_embedding_params self.assertFalse(any(res)) variables = { "x": tf.Variable(1, name="x"), "y": tf.Variable(2, name="y"), } self.params.non_embedding_params = variables self.assertTrue("x" in self.params.non_embedding_params) self.assertTrue("y" in self.params.non_embedding_params) def test_get_embedding_param(self): self.params.reset() self.params.init_embedding_params(self.infos_pb) self._test_get_embedding_param() def test_set_embedding_param(self): self.params.reset() self.params.init_embedding_params(self.infos_pb) indices = [100, 34, 8] x = len(indices) values = np.random.uniform(size=x * self.embedding_dim).reshape( (x, self.embedding_dim) ) self.params.set_embedding_param( self.embedding_table_name, indices, values ) row0 = self.params.get_embedding_param( self.embedding_table_name, [100] ) row1 = self.params.get_embedding_param(self.embedding_table_name, [34]) row2 = self.params.get_embedding_param(self.embedding_table_name, [8]) rows = [row0, row1, row2] rows = np.concatenate(rows) np.testing.assert_array_equal(rows, values) with self.assertRaises(ValueError): self.params.set_embedding_param("tom", [0, 1, 2], values) def test_check_grad(self): self.params.reset() self.params.init_from_model_pb(self.model_pb) grad0 = Tensor("z", None, None) with self.assertRaisesRegex(ValueError, "Name error"): self.params.check_grad(grad0) grad1 = Tensor("x", np.random.uniform(size=(3, 5)), None) with self.assertRaisesRegex(ValueError, "Non embedding param error"): self.params.check_grad(grad1) grad2 = Tensor( name="embedding_1", values=np.random.uniform(size=(3, 11)), indices=np.array([1, 2, 3]), ) with self.assertRaisesRegex( ValueError, "ElasticDL embedding param error" ): self.params.check_grad(grad2) grad3 = Tensor( name="x", values=np.random.uniform(size=(4, 4)), indices=np.array([1, 2, 3, 4]), ) with self.assertRaisesRegex(ValueError, "Keras embedding param error"): self.params.check_grad(grad3) def test_create_slot_params(self): # At first, no embedding table are in the parameters self.assertFalse(self.params.has_embedding_params()) # create embedding tables in the parameters self.params.init_embedding_params(self.infos_pb) self.assertTrue(self.params.has_embedding_params()) slot_names = ["accumulator", "linear"] slot_init_value = {slot_names[0]: 3.5, slot_names[1]: 0.0} self.params.create_slot_params(slot_names, slot_init_value) self._test_get_embedding_param(slot_names, slot_init_value) def test_export_to_model_pb(self): self.params.init_from_model_pb(self.model_pb) self.params.version = 15 model_pb = self.params.to_model_pb() params = Parameters() params.init_from_model_pb(model_pb) self.assertEqual(params.version, self.params.version) self.assertEqual( params.non_embedding_params.keys(), self.params.non_embedding_params.keys(), ) self.assertEqual( params.embedding_params["embedding_1"].get([0]).tolist(), self.params.embedding_params["embedding_1"].get([0]).tolist(), )