def get_data(path, isTrain, stat_file):
ds = LMDBDataPoint(path, shuffle=isTrain)
mean, std = serialize.loads(open(stat_file).read())
ds = MapDataComponent(ds, lambda x: (x - mean) / std)
ds = TIMITBatch(ds, BATCH)
if isTrain:
ds = PrefetchDataZMQ(ds, 1)
return ds
def get_data(path, isTrain, stat_file):
ds = LMDBSerializer.load(path, shuffle=isTrain)
mean, std = serialize.loads(open(stat_file, 'rb').read())
ds = MapDataComponent(ds, lambda x: (x - mean) / std)
ds = TIMITBatch(ds, BATCH)
if isTrain:
ds = MultiProcessRunnerZMQ(ds, 1)
return ds
def get_config():
logger.auto_set_dir()
ds = TIMITData()
ds = TIMITBatch(ds, BATCH)
ds = PrefetchDataZMQ(ds, 1)
step_per_epoch = ds.size()
lr = symbolic_functions.get_scalar_var('learning_rate', 1e-3, summary=True)
return TrainConfig(
dataset=ds,
#optimizer=tf.train.AdamOptimizer(lr),
optimizer=tf.train.MomentumOptimizer(lr, 0.9),
callbacks=Callbacks([
StatPrinter(),
ModelSaver(),
]),
model=Model(),
step_per_epoch=step_per_epoch,
max_epoch=100,
)