def train():
args = parse_args()
args.model_type = ModelType(
args.model_type) #--model_type=0,1 classification regression
#只使用cpu而且cpu只开一个线程
paddle.init(use_gpu=False, trainer_count=1)
'''dnn_input_dim: 61
lr_input_dim: 10040001'''
dnn_input_dim, lr_input_dim = reader.load_data_meta(args.data_meta_file)
# create ctr model.
model = CTRmodel(dnn_layer_dims,
dnn_input_dim,
lr_input_dim,
model_type=args.model_type,
is_infer=False)
params = paddle.parameters.create(model.train_cost)
optimizer = paddle.optimizer.AdaGrad() #学习率优化
trainer = paddle.trainer.SGD(cost=model.train_cost,
parameters=params,
update_equation=optimizer)
dataset = reader.Dataset()
def __event_handler__(event):
if isinstance(event, paddle.event.EndIteration):
num_samples = event.batch_id * args.batch_size
if event.batch_id % 100 == 0:
logger.warning(
"Pass %d, Samples %d, Cost %f, %s" %
(event.pass_id, num_samples, event.cost, event.metrics))
if event.batch_id % 1000 == 0:
if args.test_data_path:
result = trainer.test(reader=paddle.batch(
dataset.test(args.test_data_path),
batch_size=args.batch_size),
feeding=reader.feeding_index)
logger.warning("Test %d-%d, Cost %f, %s" %
(event.pass_id, event.batch_id, result.cost,
result.metrics))
path = "{}-pass-{}-batch-{}-test-{}.tar.gz".format(
args.model_output_prefix, event.pass_id, event.batch_id,
result.cost)
with gzip.open(path, 'w') as f:
trainer.save_parameter_to_tar(f)
trainer.train(reader=paddle.batch(paddle.reader.shuffle(dataset.train(
args.train_data_path),
buf_size=500),
batch_size=args.batch_size),
feeding=reader.feeding_index,
event_handler=__event_handler__,
num_passes=args.num_passes)
def __init__(self, param_path):
logger.info("create CTR model")
dnn_input_dim, lr_input_dim = reader.load_data_meta(args.data_meta_path)
# create the mdoel
self.ctr_model = network_conf.CTRmodel(
dnn_layer_dims,
dnn_input_dim,
lr_input_dim,
model_type=ModelType(args.model_type),
is_infer=True)
# load parameter
logger.info("load model parameters from %s" % param_path)
self.parameters = paddle.parameters.Parameters.from_tar(
gzip.open(param_path, 'r'))
self.inferer = paddle.inference.Inference(
output_layer=self.ctr_model.model,
parameters=self.parameters, )