import math
logging.basicConfig(filename="test.log",
filemode="w",
format="%(asctime)s %(name)s:%(levelname)s:%(message)s",
datefmt="%d-%M-%Y %H:%M:%S",
level=logging.DEBUG)
trainer_id = int(sys.argv[1]) # trainer id for each guest
job_path = "fl_job_config"
job = FLRunTimeJob()
job.load_trainer_job(job_path, trainer_id)
job._scheduler_ep = "127.0.0.1:9091" # Inform scheduler IP address to trainer
trainer = FLTrainerFactory().create_fl_trainer(job)
trainer._current_ep = "127.0.0.1:{}".format(9000 + trainer_id)
trainer.start()
test_program = trainer._main_program.clone(for_test=True)
train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.mnist.train(),
buf_size=500),
batch_size=64)
test_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=64)
input = fluid.layers.data(name='input', shape=[1, 28, 28], dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
feeder = fluid.DataFeeder(feed_list=[input, label], place=fluid.CPUPlace())
def train_test(train_test_program, train_test_feed, train_test_reader):
acc_set = []
for test_data in train_test_reader():
filemode="w",
format="%(asctime)s %(name)s:%(levelname)s:%(message)s",
datefmt="%d-%M-%Y %H:%M:%S",
level=logging.DEBUG)
trainer_id = int(sys.argv[1]) # trainer id for each guest
place = fluid.CPUPlace()
train_file_dir = "mid_data/node4/%d/" % trainer_id
job_path = "fl_job_config"
job = FLRunTimeJob()
job.load_trainer_job(job_path, trainer_id)
job._scheduler_ep = "127.0.0.1:9091" # Inform the scheduler IP to trainer
trainer = FLTrainerFactory().create_fl_trainer(job)
trainer._current_ep = "127.0.0.1:{}".format(9000 + trainer_id)
place = fluid.CPUPlace()
trainer.start(place)
r = Gru4rec_Reader()
train_reader = r.reader(train_file_dir, place, batch_size=125)
output_folder = "model_node4"
epoch_i = 0
while not trainer.stop():
epoch_i += 1
train_step = 0
for data in train_reader():
#print(np.array(data['src_wordseq']))
ret_avg_cost = trainer.run(feed=data, fetch=["mean_0.tmp_0"])
train_step += 1
if train_step == trainer._step:
break
batch_transforms=batch_trans,
batch_size=1,
shuffle=True,
drop_empty=True,
inputs_def=inputs_def)()
return data_loader
job_path = "fl_job_config"
job = FLRunTimeJob()
job.load_trainer_job(job_path, trainer_id)
job._scheduler_ep = "127.0.0.1:9091" # Inform scheduler IP address to trainer
trainer = FLTrainerFactory().create_fl_trainer(job)
trainer._current_ep = "127.0.0.1:{}".format(9000 + trainer_id)
trainer.start(fluid.CUDAPlace(trainer_id))
test_program = trainer._main_program.clone(for_test=True)
image = fluid.layers.data(name='image',
shape=[3, None, None],
dtype='float32',
lod_level=0)
im_info = fluid.layers.data(name='im_info',
shape=[None, 3],
dtype='float32',
lod_level=0)
im_id = fluid.layers.data(name='im_id',
shape=[None, 1],
dtype='int64',
lod_level=0)
