avg_loss_set.append(float(avg_loss_np))
acc_val_mean = numpy.array(acc_set).mean()
avg_loss_val_mean = numpy.array(avg_loss_set).mean()
return avg_loss_val_mean, acc_val_mean
# for test
while not trainer.stop():
epoch_id += 1
print("epoch %d start train" % (epoch_id))
for data in train_reader():
step_i += 1
trainer.step_id = step_i
accuracy, = trainer.run(feed=feeder.feed(data),
fetch=["accuracy_0.tmp_0"])
if step_i % 100 == 0:
print("Epoch: {0}, step: {1}, accuracy: {2}".format(
epoch_id, step_i, accuracy[0]))
print(step_i)
avg_loss_val, acc_val = train_test(train_test_program=test_program,
train_test_reader=test_reader,
train_test_feed=feeder)
print("Test with Epoch %d, avg_cost: %s, acc: %s" %
(epoch_id, avg_loss_val, acc_val))
if epoch_id > 40:
break
if epoch_id % 5 == 0:
trainer.save_inference_program(output_folder)
def compute_privacy_budget(sample_ratio, epsilon, step, delta):
E = 2 * epsilon * math.sqrt(step * sample_ratio)
print("({0}, {1})-DP".format(E, delta))
output_folder = "model_node%d" % trainer_id
epoch_id = 0
step = 0
while not trainer.stop():
epoch_id += 1
if epoch_id > 40:
break
print("epoch %d start train" % (epoch_id))
for step_id, data in enumerate(train_reader()):
cost = trainer.run(feeder.feed(data), fetch=["mean_0.tmp_0"])
step += 1
print("train cost:%.3f" % (cost[0]))
cost_val = train_test(train_test_program=test_program,
train_test_reader=test_reader,
train_test_feed=feeder)
print("Test with epoch %d, cost: %s" % (epoch_id, cost_val))
compute_privacy_budget(sample_ratio=0.001,
epsilon=0.1,
step=step,
delta=0.00001)
save_dir = (output_folder + "/epoch_%d") % epoch_id
trainer.save_inference_program(output_folder)
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
epoch_id += 1
if epoch_id % 5 == 0:
trainer.save_inference_program(output_folder)
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)
trainer = FLTrainerFactory().create_fl_trainer(job)
trainer.start()
r = Gru4rec_Reader()
train_reader = r.reader(train_file_dir, place, batch_size = 125)
output_folder = "model_node4"
step_i = 0
while not trainer.stop():
step_i += 1
print("batch %d start train" % (step_i))
for data in train_reader():
#print(np.array(data['src_wordseq']))
ret_avg_cost = trainer.run(feed=data,
fetch=["mean_0.tmp_0"])
avg_ppl = np.exp(ret_avg_cost[0])
newest_ppl = np.mean(avg_ppl)
print("ppl:%.3f" % (newest_ppl))
save_dir = (output_folder + "/epoch_%d") % step_i
if trainer_id == 0:
print("start save")
trainer.save_inference_program(save_dir)
if step_i >= 40:
break