def ctc_data():
""" Returns a provider that can be used with `ctc_model()`.
"""
number_of_samples = 11
vocab_size = 4 # Same as above
output_timesteps = 10
maximum_transcription_length = 4 # Must be <= output_timesteps
return BatchProvider(
sources={
'TEST_input':
VanillaSource(
numpy.random.uniform(low=-1,
high=1,
size=(number_of_samples, output_timesteps,
2))),
'TEST_transcription':
VanillaSource(
numpy.random.random_integers(0,
vocab_size - 1,
size=(number_of_samples,
maximum_transcription_length
))),
'TEST_input_length':
VanillaSource(
numpy.ones(shape=(number_of_samples, 1)) * output_timesteps),
'TEST_transcription_length':
VanillaSource(
numpy.random.random_integers(1,
maximum_transcription_length,
size=(number_of_samples, 1)))
})
def simple_data():
""" Returns a small provider that can be used to train the `simple_model()`.
"""
return BatchProvider(
sources={
'TEST_input': VanillaSource(numpy.random.uniform(size=(100, 10))),
'TEST_output': VanillaSource(numpy.random.uniform(size=(100, 1)))
})
def embedding_data():
""" Returns a small provider that can be used to train the
`embedding_model()`.
"""
return BatchProvider(
sources={
'TEST_input':
VanillaSource(numpy.random.random_integers(0, 99, size=(5, 10))),
'TEST_output':
VanillaSource(numpy.random.uniform(size=(5, 3)))
})
def uber_data():
""" In the land of Mordor, where the shadows lie.
Data for the uber model.
"""
return BatchProvider(
sources={
'TEST_input':
VanillaSource(
numpy.random.uniform(low=-1, high=1, size=(2, 32, 32))),
'TEST_output':
VanillaSource(numpy.random.uniform(low=-1, high=1, size=(2, 140)))
})
def ctc_eval_data(ctc_data):
""" Provides CTC data with only the evaluation-time input data available.
"""
for key, source in zip(ctc_data.keys, ctc_data.sources):
if key == 'TEST_input':
return BatchProvider(sources={key: source})
