context.set_auto_parallel_context(
device_num=device_num,
parallel_mode=ParallelMode.DATA_PARALLEL,
gradients_mean=True)
init()
else:
rank = 0
device_num = 1
mindrecord_file = args.dataset_path
if not os.path.exists(mindrecord_file):
print("dataset file {} not exists, please check!".format(
mindrecord_file))
raise ValueError(mindrecord_file)
dataset = create_gru_dataset(epoch_count=config.num_epochs,
batch_size=config.batch_size,
dataset_path=mindrecord_file,
rank_size=device_num,
rank_id=rank)
dataset_size = dataset.get_dataset_size()
print("dataset size is {}".format(dataset_size))
network = Seq2Seq(config)
network = GRUWithLossCell(network)
lr = dynamic_lr(config, dataset_size)
opt = Adam(network.trainable_params(), learning_rate=lr)
scale_manager = DynamicLossScaleManager(
init_loss_scale=config.init_loss_scale_value,
scale_factor=config.scale_factor,
scale_window=config.scale_window)
update_cell = scale_manager.get_update_cell()
netwithgrads = GRUTrainOneStepWithLossScaleCell(network, opt, update_cell)
type=int,
default=1,
help='Use device nums, default is 1')
parser.add_argument('--result_path',
type=str,
default='./preprocess_Result/',
help='result path')
args = parser.parse_args()
if __name__ == "__main__":
mindrecord_file = args.dataset_path
if not os.path.exists(mindrecord_file):
print("dataset file {} not exists, please check!".format(
mindrecord_file))
raise ValueError(mindrecord_file)
dataset = create_gru_dataset(epoch_count=config.num_epochs, batch_size=config.eval_batch_size, \
dataset_path=mindrecord_file, rank_size=args.device_num, rank_id=0, do_shuffle=False, is_training=False)
source_ids_path = os.path.join(args.result_path, "00_data")
target_ids_path = os.path.join(args.result_path, "01_data")
os.makedirs(source_ids_path)
os.makedirs(target_ids_path)
for i, data in enumerate(
dataset.create_dict_iterator(output_numpy=True, num_epochs=1)):
file_name = "gru_bs" + str(
config.eval_batch_size) + "_" + str(i) + ".bin"
data["source_ids"].tofile(os.path.join(source_ids_path, file_name))
data["target_ids"].tofile(os.path.join(target_ids_path, file_name))
print("=" * 20, "export bin files finished", "=" * 20)
str(cb_params.net_outputs[0].asnumpy()),
str(cb_params.net_outputs[1].asnumpy()),
str(cb_params.net_outputs[2].asnumpy())))
f.write('\n')
if __name__ == '__main__':
if args.run_distribute:
rank = args.rank_id
device_num = args.device_num
context.set_auto_parallel_context(device_num=device_num, parallel_mode=ParallelMode.DATA_PARALLEL,
gradients_mean=True)
init()
else:
rank = 0
device_num = 1
dataset = create_gru_dataset(epoch_count=config.num_epochs, batch_size=config.batch_size,
dataset_path=args.dataset_path, rank_size=device_num, rank_id=rank)
dataset_size = dataset.get_dataset_size()
print("dataset size is {}".format(dataset_size))
network = Seq2Seq(config)
network = GRUWithLossCell(network)
lr = dynamic_lr(config, dataset_size)
opt = Adam(network.trainable_params(), learning_rate=lr)
scale_manager = DynamicLossScaleManager(init_loss_scale=config.init_loss_scale_value,
scale_factor=config.scale_factor,
scale_window=config.scale_window)
update_cell = scale_manager.get_update_cell()
netwithgrads = GRUTrainOneStepWithLossScaleCell(network, opt, update_cell)
time_cb = TimeMonitor(data_size=dataset_size)
loss_cb = LossCallBack(rank_id=rank)
cb = [time_cb, loss_cb]
def run_gru_eval():
"""
Transformer evaluation.
"""
parser = argparse.ArgumentParser(description='GRU eval')
parser.add_argument(
"--device_target",
type=str,
default="Ascend",
help="device where the code will be implemented, default is Ascend")
parser.add_argument('--device_id',
type=int,
default=0,
help='device id of GPU or Ascend, default is 0')
parser.add_argument('--device_num',
type=int,
default=1,
help='Use device nums, default is 1')
parser.add_argument('--ckpt_file',
type=str,
default="",
help='ckpt file path')
parser.add_argument("--dataset_path",
type=str,
default="",
help="Dataset path, default: f`sns.")
args = parser.parse_args()
context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target, reserve_class_name_in_scope=False, \
device_id=args.device_id, save_graphs=False)
dataset = create_gru_dataset(epoch_count=config.num_epochs, batch_size=config.eval_batch_size, \
dataset_path=args.dataset_path, rank_size=args.device_num, rank_id=0, do_shuffle=False, is_training=False)
dataset_size = dataset.get_dataset_size()
print("dataset size is {}".format(dataset_size))
network = Seq2Seq(config, is_training=False)
network = GRUInferCell(network)
network.set_train(False)
if args.ckpt_file != "":
parameter_dict = load_checkpoint(args.ckpt_file)
load_param_into_net(network, parameter_dict)
model = Model(network)
predictions = []
source_sents = []
target_sents = []
eval_text_len = 0
for batch in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
source_sents.append(batch["source_ids"])
target_sents.append(batch["target_ids"])
source_ids = Tensor(batch["source_ids"], mstype.int32)
target_ids = Tensor(batch["target_ids"], mstype.int32)
predicted_ids = model.predict(source_ids, target_ids)
print("predicts is ", predicted_ids.asnumpy())
print("target_ids is ", target_ids)
predictions.append(predicted_ids.asnumpy())
eval_text_len = eval_text_len + 1
f_output = open(config.output_file, 'w')
f_target = open(config.target_file, "w")
for batch_out, true_sentence in zip(predictions, target_sents):
for i in range(config.eval_batch_size):
target_ids = [str(x) for x in true_sentence[i].tolist()]
f_target.write(" ".join(target_ids) + "\n")
token_ids = [str(x) for x in batch_out[i].tolist()]
f_output.write(" ".join(token_ids) + "\n")
f_output.close()
f_target.close()