def test_lookup(self):
opt = Adam()
opt_wrapper = OptimizerWrapper(opt, None, {})
embedding_dim = 4
layers = ["embedding_0", "embedding_1"]
grads = [
tf.IndexedSlices(None, tf.constant([2, 0, 2])),
tf.IndexedSlices(None, tf.constant([1, 2, 0, 2])),
]
ids_list = [[2, 0], [1, 2, 0]]
grads_and_vars = list(zip(grads, layers))
mock_kv_store = MockKvStore({})
for layer in layers:
for id in range(3):
mock_kv_store.update(
keys=[Embedding.get_key([layer, id])],
values=[np.random.rand(embedding_dim).astype(np.float32)],
)
for i, slot in enumerate(["m", "v"]):
mock_kv_store.update(
keys=[Embedding.get_key([layer, slot, id])],
values=[
np.random.rand(embedding_dim).astype(np.float32)
],
)
with mock.patch.object(
EmbeddingService, "lookup_embedding", mock_kv_store.lookup
):
embeddings, slot_values = opt_wrapper._lookup_embeddings_and_slots(
grads_and_vars
)
grad0 = grads_and_vars[0][0]
self.assertTrue((grad0.indices.numpy() == [0, 1, 0]).all())
grad1 = grads_and_vars[1][0]
self.assertTrue((grad1.indices.numpy() == [0, 1, 2, 1]).all())
for ids, layer in zip(ids_list, layers):
self.assertTrue(
(opt_wrapper._unique_ids_all_layers[layer] == ids).all()
)
values, _ = mock_kv_store.lookup(
keys=[Embedding.get_key([layer, id]) for id in ids]
)
values = np.concatenate(values).reshape(-1, embedding_dim)
self.assertTrue((embeddings[layer] - values < 0.0001).all())
for slot in ["m", "v"]:
values, _ = mock_kv_store.lookup(
keys=[Embedding.get_key([layer, slot, id]) for id in ids]
)
values = np.concatenate(values).reshape(-1, embedding_dim)
self.assertTrue(
(slot_values[layer][slot] - values < 0.0001).all()
)
def test_report_to_kv_store(self):
opt = SGD(momentum=0.1)
opt_wrapper = OptimizerWrapper(opt, None, {})
ids_list = [[1, 5], [10]]
opt_wrapper._unique_ids_all_layers = {
"test_1": np.array(ids_list[0]),
"test_2": np.array(ids_list[1]),
}
t = np.array([1.0, 1.0, 1.0])
opt_wrapper._embed_variables = {
"test_1": tf.Variable([t, t * 5]),
"test_2": tf.Variable([t * 10]),
}
opt_wrapper._slot_variables = {
"test_1": {
"momentum": tf.Variable([t / 10.0, t / 2.0])
},
"test_2": {
"momentum": tf.Variable([t])
},
}
mock_kv_store = MockKvStore({})
with mock.patch.object(EmbeddingService, "update_embedding",
mock_kv_store.update):
opt_wrapper._report_to_kv_store()
expected_mock_kv_store = MockKvStore({})
expected_mock_kv_store.update(
keys=["test_1-1", "test_1-5", "test_2-10"],
values=[t, t * 5.0, t * 10.0],
)
expected_mock_kv_store.update(
keys=[
"test_1-momentum-1",
"test_1-momentum-5",
"test_2-momentum-10",
],
values=[t / 10.0, t / 2.0, t],
)
for k, ids in zip(["test_1", "test_2"], ids_list):
for id in ids:
key = Embedding.get_key([k, id])
v, _ = mock_kv_store.lookup([key])
expected_v, _ = expected_mock_kv_store.lookup([key])
self.assertTrue((v[0] == expected_v[0]).all())
def _test_correctness(self, optimizer_class, X, Y, seed, **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
weights = self._random_init_model_weight(
[(4, 4), (4, 4), (72, 1), (1,)], seed
)
loss_fn = model_module["loss"]
model1 = model_module["KerasEmbeddingModel"](4, 4, weights)
opt1 = optimizer_class(**kwargs)
_train(model1, opt1, X, Y, loss_fn, random_seed=seed)
model2 = model_module["EdlEmbeddingModel"](4, weights[2:])
opt2 = optimizer_class(**kwargs)
layer_names = [layer.name for layer in find_layer(model2, Embedding)]
embed_dims = dict([(layer_name, 4) for layer_name in layer_names])
# intialize embedding vectors in kv store
mock_kv_store = MockKvStore({})
for layer, embed_table in zip(layer_names, weights[:2]):
for i, embed_vector in enumerate(embed_table):
mock_kv_store.update(["%s-%d" % (layer, i)], [embed_vector])
# train model with optimizer wrapper
with mock.patch.object(
EmbeddingService, "lookup_embedding", mock_kv_store.lookup
), mock.patch.object(
EmbeddingService, "update_embedding", mock_kv_store.update
):
_train_edl_embedding_with_optimizer_wrapper(
model2, opt2, X, Y, loss_fn, embed_dims, 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()
keys = [Embedding.get_key([layer2.name, i]) for i in range(4)]
w2 = np.concatenate(mock_kv_store.lookup(keys)[0]).reshape(
4, -1
)
self.assertTrue((w1 - w2 < 0.0001).all(), msg=wrong_msg)
else:
for w1, w2 in zip(layer1.weights, layer2.weights):
self.assertTrue(
(w1 - w2 < 0.0001).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)
embed_dims = {}
embed_var_n = len(embed_values)
mock_kv_store = MockKvStore()
for layer, values in embed_values.items():
embed_dims[layer] = values.shape[1]
input_dim = values.shape[0]
keys = [
Embedding.get_key([layer, idx]) for idx in range(input_dim)
]
mock_kv_store.update(keys, values)
opt = SGD(0.1)
opt_wrapper = OptimizerWrapper(opt, None, embed_dims, True)
with mock.patch.object(EmbeddingService, "lookup_embedding",
mock_kv_store.lookup), mock.patch.object(
EmbeddingService, "update_embedding",
mock_kv_store.update):
# 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():
keys = [
Embedding.get_key([layer, idx]) for idx in range(input_dim)
]
raw_value, _ = mock_kv_store.lookup(keys)
value = np.concatenate(raw_value).reshape(input_dim, -1)
self.assertTrue(
any([
np.isclose(value, expected).all()
for expected in expected_values
]))