def comparison_run(cls, runScale='full', dataScale='full_2occupations', useCPU = True):
numSeqs = EmbeddingDataReader(EmbeddingDataReader.premade_sources()[dataScale], 'bucketing', 100, 40, padToFull=True).maxXLen
params = [('initialLearningRate', [1e-3]),
('l2RegLambda', [1e-4]),
('maxNumSeqs', [numSeqs]),
('rnnCellUnitsNProbs', [([32, 32, 32], [.5]*3)]),
('convFilterSizesNKeepProbs', [([2, 3, 4], [.5]*3)]),
('convNumFeaturesPerFilter', [8]),
('pooledKeepProb', [0.5])]
cls.run_thru_data(EmbeddingDataReader, dataScale, make_params_dict(params), runScale, useCPU, padToFull=True)
def quick_run(cls, runScale ='basic', dataScale='tiny_fake_2', useCPU = True):
numSeqs = EmbeddingDataReader(EmbeddingDataReader.premade_sources()[dataScale], 'bucketing', 100, 40, padToFull=True).maxXLen
params = [('initialLearningRate', [1e-3]),
('l2RegLambda', [0]),
('maxNumSeqs', [numSeqs]),
('rnnCellUnitsNProbs', [([3], [0.9])
]),
('convFilterSizesNKeepProbs', [([2], [1.])
]),
('convNumFeaturesPerFilter', [4]),
('pooledKeepProb', [1])]
cls.run_thru_data(EmbeddingDataReader, dataScale, make_params_dict(params), runScale, useCPU, padToFull=True)
def quick_learn(cls,
runScale='small',
dataScale='small_2occupations',
useCPU=True):
numSeqs = EmbeddingDataReader(
EmbeddingDataReader.premade_sources()[dataScale],
'bucketing',
100,
40,
padToFull=True).maxXLen
params = [('initialLearningRate', [1e-3]), ('l2RegLambda', [0]),
('maxNumSeqs', [numSeqs]), ('filterSizes', [[2, 4]]),
('numFeaturesPerFilter', [3]), ('pooledKeepProb', [1])]
cls.run_thru_data(EmbeddingDataReader,
dataScale,
make_params_dict(params),
runScale,
useCPU,
padToFull=True)
def comparison_run(cls,
runScale='medium',
dataScale='full_2occupations',
useCPU=True):
numSeqs = EmbeddingDataReader(
EmbeddingDataReader.premade_sources()[dataScale],
'bucketing',
100,
40,
padToFull=True).maxXLen
params = [('initialLearningRate', [1e-3]), ('l2RegLambda', [1e-6]),
('maxNumSeqs', [numSeqs]),
('filterSizesNKeepProbs', [([1, 2, 3,
4], [0.9, 0.9, 0.9, 0.9])]),
('numFeaturesPerFilter', [128]),
('pooledKeepProb', [0.5, 0.85, 1])]
cls.run_thru_data(EmbeddingDataReader,
dataScale,
make_params_dict(params),
runScale,
useCPU,
padToFull=True)
def quick_learn(cls,
runScale='small',
dataScale='small_2occupations',
useCPU=True):
numSeqs = EmbeddingDataReader(
EmbeddingDataReader.premade_sources()[dataScale],
'bucketing',
100,
40,
padToFull=True).maxXLen
params = [('initialLearningRate', [1e-3]), ('l2RegLambda', [1e-4]),
('maxNumSeqs', [numSeqs]),
('convFilterShapesNKeepProbs', [([(3, -1)], [1])]),
('convNumFeaturesPerFilter', [32]),
('rnnCellUnitsNProbs', [([16], [0.9])])]
cls.run_thru_data(EmbeddingDataReader,
dataScale,
make_params_dict(params),
runScale,
useCPU,
padToFull=True)