level=logging.DEBUG) logger = logging.getLogger("FLTrainer") BATCH_SIZE = 64 train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.mnist.train(), buf_size=500), batch_size=BATCH_SIZE) test_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=BATCH_SIZE) trainer_num = 2 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 the scheduler IP to trainer trainer = FLTrainerFactory().create_fl_trainer(job) trainer.trainer_id = trainer_id trainer._current_ep = "127.0.0.1:{}".format(9000 + trainer_id) trainer.trainer_num = trainer_num trainer.key_dir = "./keys/" trainer.start() output_folder = "fl_model" epoch_id = 0 step_i = 0 inputs = fluid.layers.data(name='x', shape=[1, 28, 28], dtype='float32') label = fluid.layers.data(name='y', shape=[1], dtype='int64') feeder = fluid.DataFeeder(feed_list=[inputs, label], place=fluid.CPUPlace())
server._current_ep = endpoint server.start() else: def reader(): for i in range(1000): data_dict = {} for i in range(3): data_dict[str(i)] = np.random.rand(1, 5).astype('float32') data_dict["label"] = np.random.randint(2, size=(1, 1)).astype('int64') yield data_dict trainer_id = message.split("trainer")[1] job_path = "job_config" job = FLRunTimeJob() job.load_trainer_job(job_path, int(trainer_id)) job._scheduler_ep = scheduler_conf["ENDPOINT"] trainer = FLTrainerFactory().create_fl_trainer(job) trainer._current_ep = endpoint trainer.start() print(trainer._scheduler_ep, trainer._current_ep) output_folder = "fl_model" epoch_id = 0 while not trainer.stop(): print("batch %d start train" % (step_i)) step_i = 0 for data in reader(): trainer.run(feed=data, fetch=[]) step_i += 1 if train_step == trainer._step: break