def main(args):
"""main"""
paddle.enable_static()
model_config = json.load(open(args.model_config, 'r'))
exe_params = default_exe_params(False, args.use_cuda, args.thread_num)
exe = exe_params['exe']
trainer_num = exe_params['trainer_num']
trainer_id = exe_params['trainer_id']
places = exe_params['places']
task = model_config['task']
model = TAPEModel(model_config=model_config, name=task)
test_program = fluid.Program()
test_startup = fluid.Program()
with fluid.program_guard(test_program, test_startup):
with fluid.unique_name.guard():
model.forward(True)
model.cal_loss()
test_data_loader = setup_data_loader(model.input_list,
model_config, args.test_data,
trainer_id, trainer_num,
places, args.batch_size)
exe.run(test_startup)
test_metric = get_metric(task)
if not args.init_model is None and args.init_model != "":
load_partial_params(exe, args.init_model, test_program)
else:
raise RuntimeError('Please set init_model.')
test_fetch_list = model.get_fetch_list(),
for data in test_data_loader():
results = exe.run(program=test_program,
feed=data,
fetch_list=test_fetch_list,
return_numpy=False)
update_metric(task, test_metric, results)
test_metric.show()
def main(args):
paddle.enable_static()
model_config = json.load(open(args.model_config, 'r'))
exe_params = default_exe_params(args.is_distributed, args.use_cuda,
args.thread_num)
exe = exe_params['exe']
trainer_num = exe_params['trainer_num']
trainer_id = exe_params['trainer_id']
dist_strategy = exe_params['dist_strategy']
places = exe_params['places']
task = model_config['task']
model = TAPEModel(model_config=model_config, name=task)
train_program = fluid.Program()
train_startup = fluid.Program()
with fluid.program_guard(train_program, train_startup):
with fluid.unique_name.guard():
model.forward(False)
model.cal_loss()
optimizer = default_optimizer(args.lr, args.warmup_steps,
args.max_grad_norm)
setup_optimizer(optimizer, model, args.use_cuda,
args.is_distributed, dist_strategy)
optimizer.minimize(model.loss)
train_data_loader = setup_data_loader(model.input_list,
model_config,
args.train_data, trainer_id,
trainer_num, places,
args.batch_size)
exe.run(train_startup)
train_metric = get_metric(task)
train_fetch_list = model.get_fetch_list()
if args.test_data is not None:
test_program = fluid.Program()
test_startup = fluid.Program()
with fluid.program_guard(test_program, test_startup):
with fluid.unique_name.guard():
model.forward(True)
model.cal_loss()
test_data_loader = setup_data_loader(model, model_config,
args.test_data,
trainer_id, trainer_num,
places, args.batch_size)
exe.run(test_startup)
test_metric = get_metric(task)
test_fetch_list = model.get_fetch_list()
if not args.is_distributed:
train_program = fluid.compiler.CompiledProgram(
train_program).with_data_parallel(loss_name=model.loss.name)
if args.test_data is not None and args.test_data != "":
test_program = fluid.compiler.CompiledProgram(
test_program).with_data_parallel(loss_name=model.loss.name)
if args.init_model is not None and args.init_model != "":
load_partial_params(exe, args.init_model, test_program)
for epoch_id in range(args.max_epoch):
print(time.time(), 'Start epoch %d' % epoch_id)
print('Train:')
train_metric.clear()
for data in train_data_loader():
results = exe.run(program=train_program,
feed=data,
fetch_list=train_fetch_list,
return_numpy=False)
update_metric(task, train_metric, results)
train_metric.show()
print()
if args.test_data is not None and args.test_data != "":
print('Test:')
test_metric.clear()
for data in test_data_loader():
results = exe.run(program=test_program,
feed=data,
fetch_list=test_fetch_list,
return_numpy=False)
update_metric(task, test_metric, results)
test_metric.show()
print()
if trainer_id == 0:
print(time.time(), "Save model epoch%d." % epoch_id)
is_exist = os.path.exists(args.model_dir)
if not is_exist:
os.makedirs(args.model_dir)
fluid.io.save_params(exe,
'%s/epoch%d' % (args.model_dir, epoch_id),
train_program)