def test_get_embedding(self):
"""Tests :func:`~texar.torch.modules.embedder.embedder_utils.get_embedding`.
"""
vocab_size = 100
emb = embedder_utils.get_embedding(num_embeds=vocab_size)
self.assertEqual(emb.size(0), vocab_size)
self.assertEqual(emb.size(1),
embedder_utils.default_embedding_hparams()["dim"])
hparams = {
"initializer": {
"type": "torch.nn.init.uniform_",
"kwargs": {
'a': -0.1,
'b': 0.1
}
}
}
emb = embedder_utils.get_embedding(
hparams=hparams,
num_embeds=vocab_size,
)
self.assertEqual(emb.size(0), vocab_size)
self.assertEqual(emb.size(1),
embedder_utils.default_embedding_hparams()["dim"])
def default_hparams():
r"""Returns a dictionary of hyperparameters with default values.
.. code-block:: python
{
"dim": 100,
"initializer": {
"type": "random_uniform_initializer",
"kwargs": {
"minval": -0.1,
"maxval": 0.1,
"seed": None
}
},
"dropout_rate": 0,
"name": "position_embedder"
}
The hyperparameters have the same meaning as those in
:meth:`texar.torch.modules.WordEmbedder.default_hparams`.
"""
hparams = embedder_utils.default_embedding_hparams()
hparams["name"] = "position_embedder"
return hparams
def default_hparams():
# TODO Shibiao: add regularizer
r"""Returns a dictionary of hyperparameters with default values.
.. code-block:: python
{
"dim": 100,
"dropout_rate": 0,
"dropout_strategy": 'element',
"initializer": {
"type": "random_uniform_initializer",
"kwargs": {
"minval": -0.1,
"maxval": 0.1,
"seed": None
}
},
"name": "word_embedder",
}
Here:
`"dim"`: int or list
Embedding dimension. Can be a list of integers to yield embeddings
with dimensionality > 1.
Ignored if :attr:`init_value` is given to the embedder constructor.
`"dropout_rate"`: float
The dropout rate between 0 and 1. For example, ``dropout_rate=0.1``
would zero out 10% of the embeddings. Set to 0 to disable dropout.
`"dropout_strategy"`: str
The dropout strategy. Can be one of the following
- ``"element"``: The regular strategy that drops individual elements
in the embedding vectors.
- ``"item"``: Drops individual items (e.g., words) entirely. For
example, for the word sequence "the simpler the better", the
strategy can yield "_ simpler the better", where the first "the"
is dropped.
- ``"item_type"``: Drops item types (e.g., word types). For example,
for the above sequence, the strategy can yield "_ simpler _
better", where the word type "the" is dropped. The dropout will
never yield "_ simpler the better" as in the ``"item"`` strategy.
`"initializer"`: dict or None
Hyperparameters of the initializer for embedding values. See
:func:`~texar.torch.core.get_initializer` for the details. Ignored
if :attr:`init_value` is given to the embedder constructor.
`"name"`: str
Name of the embedding variable.
"""
hparams = embedder_utils.default_embedding_hparams()
hparams["name"] = "word_embedder"
return hparams