self.loss = fluid.layers.reduce_mean(self.sum_cost)
self.startup_program = fluid.default_startup_program()
inputs = [fluid.layers.data( \
name=str(slot_id), shape=[5],
dtype="float32")
for slot_id in range(3)]
label = fluid.layers.data( \
name="label",
shape=[1],
dtype='int64')
model = Model()
model.mlp(inputs, label)
job_generator = JobGenerator()
optimizer = fluid.optimizer.SGD(learning_rate=0.1)
job_generator.set_optimizer(optimizer)
job_generator.set_losses([model.loss])
job_generator.set_startup_program(model.startup_program)
job_generator.set_infer_feed_and_target_names([x.name for x in inputs],
[model.predict.name])
build_strategy = FLStrategyFactory()
build_strategy.fed_avg = True
build_strategy.inner_step = 10
strategy = build_strategy.create_fl_strategy()
# endpoints will be collected through the cluster
# in this example, we suppose endpoints have been collected
endpoints = ["127.0.0.1:8181"]
low=init_low_bound,
high=init_high_bound),
learning_rate=fc_lr_x))
cost = fluid.layers.cross_entropy(input=self.fc,
label=self.dst_wordseq)
self.acc = fluid.layers.accuracy(input=self.fc,
label=self.dst_wordseq,
k=20)
self.loss = fluid.layers.mean(x=cost)
self.startup_program = fluid.default_startup_program()
model = Model()
model.gru4rec_network()
job_generator = JobGenerator()
optimizer = fluid.optimizer.SGD(learning_rate=2.0)
job_generator.set_optimizer(optimizer)
job_generator.set_losses([model.loss])
job_generator.set_startup_program(model.startup_program)
job_generator.set_infer_feed_and_target_names(
[model.src_wordseq.name, model.dst_wordseq.name],
[model.loss.name, model.acc.name])
build_strategy = FLStrategyFactory()
build_strategy.fed_avg = True
build_strategy.inner_step = 1
strategy = build_strategy.create_fl_strategy()
# endpoints will be collected through the cluster
# in this example, we suppose endpoints have been collected
def job_generate():
#generate a fl job which is the same as fl_master
inputs = [fluid.layers.data( \
name=str(slot_id), shape=[5],
dtype="float32")
for slot_id in range(3)]
label = fluid.layers.data( \
name="label",
shape=[1],
dtype='int64')
model = Model()
model.mlp(inputs, label)
job_generator = JobGenerator()
optimizer = fluid.optimizer.SGD(learning_rate=0.1)
job_generator.set_optimizer(optimizer)
job_generator.set_losses([model.loss])
job_generator.set_startup_program(model.startup_program)
job_generator.set_infer_feed_and_target_names(
[x.name for x in inputs], [model.predict.name])
build_strategy = FLStrategyFactory()
build_strategy.fed_avg = True
build_strategy.inner_step = 10
strategy = build_strategy.create_fl_strategy()
# endpoints will be collected through the cluster
# in this example, we suppose endpoints have been collected
server_ip = ["{}".format(ip_list[0])]
output = "job_config"
job_generator.generate_fl_job(
strategy, server_endpoints=server_ip, worker_num=int(default_dict["worker_nodes"]), output=output)
file_list = os.listdir(output)
for file in file_list:
tar = tarfile.open('{}/{}.tar.gz'.format(output,file),'w:gz')
for root,dir,files in os.walk("{}/{}".format(output,file)):
for f in files:
fullpath = os.path.join(root,f)
tar.add(fullpath)
tar.close()
#self.accuracy = fluid.layers.accuracy(input=self.predict, label=self.label)
#self.loss = fluid.layers.mean(self.sum_cost)
self.startup_program = fluid.default_startup_program()
model = Model()
model.lr_network()
STEP_EPSILON = 0.1
DELTA = 0.00001
SIGMA = math.sqrt(2.0 * math.log(1.25 / DELTA)) / STEP_EPSILON
CLIP = 4.0
batch_size = 64
job_generator = JobGenerator()
optimizer = fluid.optimizer.SGD(learning_rate=0.1)
job_generator.set_optimizer(optimizer)
job_generator.set_losses([model.avg_cost])
job_generator.set_startup_program(model.startup_program)
job_generator.set_infer_feed_and_target_names(
[model.inputs.name, model.label.name], [model.avg_cost.name])
build_strategy = FLStrategyFactory()
build_strategy.dpsgd = True
build_strategy.inner_step = 1
strategy = build_strategy.create_fl_strategy()
strategy.learning_rate = 0.1
strategy.clip = CLIP
strategy.batch_size = float(batch_size)
strategy.sigma = CLIP * SIGMA
