def testIncompatibleShapes(self):
with self.test_session():
x, _, _ = _EmbeddingParams(1, 10, dtype=dtypes.float32)
sp_ids = sparse_tensor_lib.SparseTensor(
constant_op.constant([[0, 0], [0, 1], [1, 0]], dtypes.int64),
constant_op.constant([0, 1, 2], dtypes.int32),
constant_op.constant([2, 2], dtypes.int64))
sp_weights = sparse_tensor_lib.SparseTensor(
constant_op.constant([[0, 0], [0, 1]], dtypes.int64),
constant_op.constant([12.0, 5.0], dtypes.float32),
constant_op.constant([1, 2], dtypes.int64))
with self.assertRaises(ValueError):
embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
x, sp_ids, sp_weights, combiner="mean")
def testIncompatibleShapes(self):
with self.cached_session():
x, _, _ = _EmbeddingParams(1, 10, dtype=dtypes.float32)
sp_ids = sparse_tensor_lib.SparseTensor(
constant_op.constant([[0, 0], [0, 1], [1, 0]], dtypes.int64),
constant_op.constant([0, 1, 2], dtypes.int32),
constant_op.constant([2, 2], dtypes.int64))
sp_weights = sparse_tensor_lib.SparseTensor(
constant_op.constant([[0, 0], [0, 1]], dtypes.int64),
constant_op.constant([12.0, 5.0], dtypes.float32),
constant_op.constant([1, 2], dtypes.int64))
with self.assertRaises(ValueError):
embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
x, sp_ids, sp_weights, combiner="mean")
def testGradientsEmbeddingLookupSparse(self):
vocab_size = 12
batch_size = 4
param_shape = [2, 3]
sp_ids, sp_weights, _, _, _ = (self._RandomIdsAndWeights(
batch_size, vocab_size))
for num_shards, combiner, dtype, ignore_weights in itertools.product(
[1, 3], ["sum", "mean", "sqrtn"], [dtypes.float32, dtypes.float64],
[True, False]):
with self.test_session():
x, params, _ = _EmbeddingParams(num_shards,
vocab_size,
shape=param_shape,
dtype=dtype)
y = embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
x,
sp_ids,
None if ignore_weights else sp_weights,
combiner=combiner)
x_name = [_PName(i) for i in range(num_shards)]
x_init_value = [params[x_n + ":0"] for x_n in x_name]
x_shape = [i.shape for i in x_init_value]
y_shape = [batch_size] + list(
params[_PName(0) + ":0"].shape[1:])
err = gradient_checker.compute_gradient_error(
x, x_shape, y, y_shape, x_init_value=x_init_value)
self.assertLess(err, 1e-5 if dtype == dtypes.float64 else 2e-3)
def testGradientsEmbeddingLookupSparse(self):
vocab_size = 12
batch_size = 4
param_shape = [2, 3]
sp_ids, sp_weights, _, _, _ = (self._RandomIdsAndWeights(
batch_size, vocab_size))
for num_shards, combiner, dtype, ignore_weights in itertools.product(
[1, 3], ["sum", "mean", "sqrtn"], [dtypes.float32,
dtypes.float64], [True, False]):
with self.cached_session():
x, params, _ = _EmbeddingParams(
num_shards, vocab_size, shape=param_shape, dtype=dtype)
y = embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
x,
sp_ids,
None if ignore_weights else sp_weights,
combiner=combiner)
x_name = [_PName(i) for i in range(num_shards)]
x_init_value = [params[x_n + ":0"] for x_n in x_name]
x_shape = [i.shape for i in x_init_value]
y_shape = [batch_size] + list(params[_PName(0) + ":0"].shape[1:])
err = gradient_checker.compute_gradient_error(
x, x_shape, y, y_shape, x_init_value=x_init_value)
self.assertLess(err, 1e-5 if dtype == dtypes.float64 else 2e-3)
def testEmbeddingLookupSparse(self):
vocab_size = 13
batch_size = 10
param_shape = [2, 5]
expected_lookup_result_shape = [None] + param_shape
sp_ids, sp_weights, ids, weights, vals_per_batch_entry = (
self._RandomIdsAndWeights(batch_size, vocab_size))
grouped_ids = self._GroupByBatchEntry(ids, vals_per_batch_entry)
grouped_weights = self._GroupByBatchEntry(weights,
vals_per_batch_entry)
grouped_ignored_weights = self._GroupByBatchEntry(
np.ones(np.sum(vals_per_batch_entry)), vals_per_batch_entry)
for num_shards, combiner, dtype, ignore_weights in itertools.product(
[1, 5], ["sum", "mean", "sqrtn"], [dtypes.float32, dtypes.float64],
[True, False]):
with self.test_session():
p, params, feed_dict = _EmbeddingParams(num_shards,
vocab_size,
shape=param_shape,
dtype=dtype)
embedding_sum = \
embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
p,
sp_ids,
None if ignore_weights else sp_weights,
combiner=combiner)
self.assertEqual(embedding_sum.get_shape().as_list(),
expected_lookup_result_shape)
tf_embedding_sum = embedding_sum.eval(feed_dict=feed_dict)
np_embedding_sum, np_weight_sum, np_weight_sq_sum = _EmbeddingResult(
params,
grouped_ids,
num_shards,
vocab_size,
weight_vals=grouped_ignored_weights
if ignore_weights else grouped_weights)
if combiner == "mean":
np_embedding_sum /= np.reshape(np_weight_sum,
(batch_size, 1, 1))
if combiner == "sqrtn":
np_embedding_sum /= np.reshape(np.sqrt(np_weight_sq_sum),
(batch_size, 1, 1))
self.assertAllClose(np_embedding_sum, tf_embedding_sum)
def testEmbeddingLookupSparse(self):
vocab_size = 13
batch_size = 10
param_shape = [2, 5]
expected_lookup_result_shape = param_shape
sp_ids, sp_weights, ids, weights, vals_per_batch_entry = (
self._RandomIdsAndWeights(batch_size, vocab_size))
grouped_ids = self._GroupByBatchEntry(ids, vals_per_batch_entry)
grouped_weights = self._GroupByBatchEntry(weights, vals_per_batch_entry)
grouped_ignored_weights = self._GroupByBatchEntry(
np.ones(np.sum(vals_per_batch_entry)), vals_per_batch_entry)
for num_shards, combiner, dtype, ignore_weights in itertools.product(
[1, 5], ["sum", "mean", "sqrtn"], [dtypes.float32,
dtypes.float64], [True, False]):
with self.cached_session():
p, params, feed_dict = _EmbeddingParams(
num_shards, vocab_size, shape=param_shape, dtype=dtype)
embedding_sum = \
embedding_ops.embedding_lookup_sparse_with_distributed_aggregation(
p,
sp_ids,
None if ignore_weights else sp_weights,
combiner=combiner)
self.assertEqual(embedding_sum.get_shape().as_list()[1:],
expected_lookup_result_shape)
tf_embedding_sum = embedding_sum.eval(feed_dict=feed_dict)
np_embedding_sum, np_weight_sum, np_weight_sq_sum = _EmbeddingResult(
params,
grouped_ids,
num_shards,
vocab_size,
weight_vals=grouped_ignored_weights
if ignore_weights else grouped_weights)
if combiner == "mean":
np_embedding_sum /= np.reshape(np_weight_sum, (batch_size, 1, 1))
if combiner == "sqrtn":
np_embedding_sum /= np.reshape(
np.sqrt(np_weight_sq_sum), (batch_size, 1, 1))
self.assertAllClose(np_embedding_sum, tf_embedding_sum)