Skip to content

[seq2seq] fix float64 tests #419

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 15, 2019
Merged

[seq2seq] fix float64 tests #419

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions tensorflow_addons/seq2seq/attention_wrapper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1538,7 +1538,8 @@ def __init__(self,
initial_cell_state=None,
name=None,
attention_layer=None,
attention_fn=None):
attention_fn=None,
**kwargs):
"""Construct the `AttentionWrapper`.

**NOTE** If you are using the `BeamSearchDecoder` with a cell wrapped
Expand Down Expand Up @@ -1619,6 +1620,7 @@ def __init__(self,
attention_layer) and outputs (attention, alignments,
next_attention_state). If provided, the attention_layer_size should
be the size of the outputs of attention_fn.
**kwargs: Other keyword arguments for layer creation.

Raises:
TypeError: `attention_layer_size` is not None and
Expand All @@ -1629,7 +1631,7 @@ def __init__(self,
of `attention_layer_size`; if `attention_layer_size` and
`attention_layer` are set simultaneously.
"""
super(AttentionWrapper, self).__init__(name=name)
super(AttentionWrapper, self).__init__(name=name, **kwargs)
rnn_cell_impl.assert_like_rnncell("cell", cell)
if isinstance(attention_mechanism, (list, tuple)):
self._is_multi = True
Expand Down
20 changes: 10 additions & 10 deletions tensorflow_addons/seq2seq/attention_wrapper_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -466,8 +466,7 @@ def _testWithMaybeMultiAttention(self,
expected_final_alignment_history,
final_alignment_history_info)

# TODO: #407 Float64 test is failing
@parameterized.parameters([np.float32])
@parameterized.parameters([np.float32, np.float64])
def testBahdanauNormalizedDType(self, dtype):
encoder_outputs = self.encoder_outputs.astype(dtype)
decoder_inputs = self.decoder_inputs.astype(dtype)
Expand All @@ -478,11 +477,12 @@ def testBahdanauNormalizedDType(self, dtype):
normalize=True,
dtype=dtype)
cell = keras.layers.LSTMCell(
self.units, recurrent_activation="sigmoid")
cell = wrapper.AttentionWrapper(cell, attention_mechanism)
self.units, recurrent_activation="sigmoid", dtype=dtype)
cell = wrapper.AttentionWrapper(cell, attention_mechanism, dtype=dtype)

sampler = sampler_py.TrainingSampler()
my_decoder = basic_decoder.BasicDecoder(cell=cell, sampler=sampler)
my_decoder = basic_decoder.BasicDecoder(
cell=cell, sampler=sampler, dtype=dtype)

final_outputs, final_state, _ = my_decoder(
decoder_inputs,
Expand All @@ -493,8 +493,7 @@ def testBahdanauNormalizedDType(self, dtype):
self.assertEqual(final_outputs.rnn_output.dtype, dtype)
self.assertIsInstance(final_state, wrapper.AttentionWrapperState)

# TODO: #407 Float64 test is failing
@parameterized.parameters([np.float32])
@parameterized.parameters([np.float32, np.float64])
def testLuongScaledDType(self, dtype):
# Test case for GitHub issue 18099
encoder_outputs = self.encoder_outputs.astype(dtype)
Expand All @@ -507,11 +506,12 @@ def testLuongScaledDType(self, dtype):
dtype=dtype,
)
cell = keras.layers.LSTMCell(
self.units, recurrent_activation="sigmoid")
cell = wrapper.AttentionWrapper(cell, attention_mechanism)
self.units, recurrent_activation="sigmoid", dtype=dtype)
cell = wrapper.AttentionWrapper(cell, attention_mechanism, dtype=dtype)

sampler = sampler_py.TrainingSampler()
my_decoder = basic_decoder.BasicDecoder(cell=cell, sampler=sampler)
my_decoder = basic_decoder.BasicDecoder(
cell=cell, sampler=sampler, dtype=dtype)

final_outputs, final_state, _ = my_decoder(
decoder_inputs,
Expand Down