def predict(dataset):
print 'STEP 4 start...'
train_rnnrbm(dataset=dataset,
hidden_layers_sizes=params['STEP4']['hidden_layers_size'],
hidden_recurrent=params['STEP4']['hidden_recurrent'],
pretrain_lr=params['STEP4']['pretrain']['learning_rate'],
pretrain_batch_size=params['STEP4']['pretrain']['batch_size'],
pretrain_epochs=params['STEP4']['pretrain']['epochs'],
finetune_lr=params['STEP4']['finetune']['learning_rate'],
finetune_batch_size=params['STEP4']['finetune']['batch_size'],
finetune_epochs=params['STEP4']['finetune']['epochs'])
def predict(dataset):
print 'STEP 4 start...'
train_rnnrbm(dataset=dataset,
hidden_layers_sizes=params['STEP4']['hidden_layers_size'],
hidden_recurrent = params['STEP4']['hidden_recurrent'],
pretrain_lr=params['STEP4']['pretrain']['learning_rate'],
pretrain_batch_size=params['STEP4']['pretrain']['batch_size'],
pretrain_epochs=params['STEP4']['pretrain']['epochs'],
finetune_lr=params['STEP4']['finetune']['learning_rate'],
finetune_batch_size=params['STEP4']['finetune']['batch_size'],
finetune_epochs=params['STEP4']['finetune']['epochs']
)
'learning_rate']:
for epochs_pretrain in params['STEP4']['pretrain'][
'epochs']:
for batch_size_finetune in params['STEP4'][
'finetune']['batch_size']:
for learning_rate_finetune in params['STEP4'][
'finetune']['learning_rate']:
for epochs_finetune in params['STEP4'][
'finetune']['epochs']:
result = train_rnnrbm(
dataset=dataset,
hidden_layers_sizes=
hidden_layers_sizes,
hidden_recurrent=hidden_recurrent,
pretrain_lr=learning_rate_pretrain,
pretrain_batch_size=
batch_size_pretrain,
pretrain_epochs=epochs_pretrain,
finetune_lr=learning_rate_finetune,
finetune_batch_size=
batch_size_finetune,
finetune_epochs=epochs_finetune)
i += 1
print '%d / %d is done...' % (i,
all_size)
out = open(model_dirs['STEP4_logs'],
'a')
out.write(
'%f,%s,%s,%s,%d,%f,%d,%d,%f,%d\n' %
(result, brandcode,
str(hidden_layers_sizes),