def run_squad():
"""run squad task"""
parser = argparse.ArgumentParser(description="run classifier")
parser.add_argument("--device_target", type=str, default="Ascend", help="Device type, default is Ascend")
parser.add_argument("--do_train", type=str, default="false", help="Eable train, default is false")
parser.add_argument("--do_eval", type=str, default="false", help="Eable eval, default is false")
parser.add_argument("--device_id", type=int, default=0, help="Device id, default is 0.")
parser.add_argument("--epoch_num", type=int, default="1", help="Epoch number, default is 1.")
parser.add_argument("--num_class", type=int, default="2", help="The number of class, default is 2.")
parser.add_argument("--train_data_shuffle", type=str, default="true",
help="Enable train data shuffle, default is true")
parser.add_argument("--eval_data_shuffle", type=str, default="false",
help="Enable eval data shuffle, default is false")
parser.add_argument("--vocab_file_path", type=str, default="", help="Vocab file path")
parser.add_argument("--eval_json_path", type=str, default="", help="Evaluation json file path, can be eval.json")
parser.add_argument("--save_finetune_checkpoint_path", type=str, default="", help="Save checkpoint path")
parser.add_argument("--load_pretrain_checkpoint_path", type=str, default="", help="Load checkpoint file path")
parser.add_argument("--load_finetune_checkpoint_path", type=str, default="", help="Load checkpoint file path")
parser.add_argument("--train_data_file_path", type=str, default="",
help="Data path, it is better to use absolute path")
parser.add_argument("--eval_data_file_path", type=str, default="",
help="Data path, it is better to use absolute path")
parser.add_argument("--schema_file_path", type=str, default="",
help="Schema path, it is better to use absolute path")
args_opt = parser.parse_args()
epoch_num = args_opt.epoch_num
load_pretrain_checkpoint_path = args_opt.load_pretrain_checkpoint_path
save_finetune_checkpoint_path = args_opt.save_finetune_checkpoint_path
load_finetune_checkpoint_path = args_opt.load_finetune_checkpoint_path
if args_opt.do_train.lower() == "false" and args_opt.do_eval.lower() == "false":
raise ValueError("At least one of 'do_train' or 'do_eval' must be true")
if args_opt.do_train.lower() == "true" and args_opt.train_data_file_path == "":
raise ValueError("'train_data_file_path' must be set when do finetune task")
if args_opt.do_eval.lower() == "true":
if args_opt.eval_data_file_path == "":
raise ValueError("'eval_data_file_path' must be set when do evaluation task")
if args_opt.vocab_file_path == "":
raise ValueError("'vocab_file_path' must be set when do evaluation task")
if args_opt.eval_json_path == "":
raise ValueError("'tokenization_file_path' must be set when do evaluation task")
target = args_opt.device_target
if target == "Ascend":
context.set_context(mode=context.GRAPH_MODE, device_target="Ascend", device_id=args_opt.device_id)
elif target == "GPU":
context.set_context(mode=context.GRAPH_MODE, device_target="GPU")
if bert_net_cfg.compute_type != mstype.float32:
logger.warning('GPU only support fp32 temporarily, run with fp32.')
bert_net_cfg.compute_type = mstype.float32
else:
raise Exception("Target error, GPU or Ascend is supported.")
netwithloss = BertSquad(bert_net_cfg, True, 2, dropout_prob=0.1)
if args_opt.do_train.lower() == "true":
ds = create_squad_dataset(batch_size=bert_net_cfg.batch_size, repeat_count=1,
data_file_path=args_opt.train_data_file_path,
schema_file_path=args_opt.schema_file_path,
do_shuffle=(args_opt.train_data_shuffle.lower() == "true"))
do_train(ds, netwithloss, load_pretrain_checkpoint_path, save_finetune_checkpoint_path, epoch_num)
if args_opt.do_eval.lower() == "true":
if save_finetune_checkpoint_path == "":
load_finetune_checkpoint_dir = _cur_dir
else:
load_finetune_checkpoint_dir = make_directory(save_finetune_checkpoint_path)
load_finetune_checkpoint_path = LoadNewestCkpt(load_finetune_checkpoint_dir,
ds.get_dataset_size(), epoch_num, "squad")
if args_opt.do_eval.lower() == "true":
ds = create_squad_dataset(batch_size=bert_net_cfg.batch_size, repeat_count=1,
data_file_path=args_opt.eval_data_file_path,
schema_file_path=args_opt.schema_file_path, is_training=False,
do_shuffle=(args_opt.eval_data_shuffle.lower() == "true"))
do_eval(ds, args_opt.vocab_file_path, args_opt.eval_json_path,
load_finetune_checkpoint_path, bert_net_cfg.seq_length)
def run_squad():
"""run squad task"""
parser = argparse.ArgumentParser(description="run squad")
parser.add_argument("--device_target",
type=str,
default="Ascend",
choices=["Ascend", "GPU"],
help="Device type, default is Ascend")
parser.add_argument("--do_train",
type=str,
default="false",
choices=["true", "false"],
help="Eable train, default is false")
parser.add_argument("--do_eval",
type=str,
default="false",
choices=["true", "false"],
help="Eable eval, default is false")
parser.add_argument("--device_id",
type=int,
default=0,
help="Device id, default is 0.")
parser.add_argument("--epoch_num",
type=int,
default=3,
help="Epoch number, default is 1.")
parser.add_argument("--num_class",
type=int,
default=2,
help="The number of class, default is 2.")
parser.add_argument("--train_data_shuffle",
type=str,
default="true",
choices=["true", "false"],
help="Enable train data shuffle, default is true")
parser.add_argument("--eval_data_shuffle",
type=str,
default="false",
choices=["true", "false"],
help="Enable eval data shuffle, default is false")
parser.add_argument("--train_batch_size",
type=int,
default=32,
help="Train batch size, default is 32")
parser.add_argument("--eval_batch_size",
type=int,
default=1,
help="Eval batch size, default is 1")
parser.add_argument("--vocab_file_path",
type=str,
default="",
help="Vocab file path")
parser.add_argument("--eval_json_path",
type=str,
default="",
help="Evaluation json file path, can be eval.json")
parser.add_argument("--save_finetune_checkpoint_path",
type=str,
default="",
help="Save checkpoint path")
parser.add_argument("--load_pretrain_checkpoint_path",
type=str,
default="",
help="Load checkpoint file path")
parser.add_argument("--load_finetune_checkpoint_path",
type=str,
default="",
help="Load checkpoint file path")
parser.add_argument("--train_data_file_path",
type=str,
default="",
help="Data path, it is better to use absolute path")
parser.add_argument("--schema_file_path",
type=str,
default="",
help="Schema path, it is better to use absolute path")
args_opt = parser.parse_args()
epoch_num = args_opt.epoch_num
load_pretrain_checkpoint_path = args_opt.load_pretrain_checkpoint_path
save_finetune_checkpoint_path = args_opt.save_finetune_checkpoint_path
load_finetune_checkpoint_path = args_opt.load_finetune_checkpoint_path
if args_opt.do_train.lower() == "false" and args_opt.do_eval.lower(
) == "false":
raise ValueError(
"At least one of 'do_train' or 'do_eval' must be true")
if args_opt.do_train.lower(
) == "true" and args_opt.train_data_file_path == "":
raise ValueError(
"'train_data_file_path' must be set when do finetune task")
if args_opt.do_eval.lower() == "true":
if args_opt.vocab_file_path == "":
raise ValueError(
"'vocab_file_path' must be set when do evaluation task")
if args_opt.eval_json_path == "":
raise ValueError(
"'tokenization_file_path' must be set when do evaluation task")
target = args_opt.device_target
if target == "Ascend":
context.set_context(mode=context.GRAPH_MODE,
device_target="Ascend",
device_id=args_opt.device_id)
elif target == "GPU":
context.set_context(mode=context.GRAPH_MODE, device_target="GPU")
if bert_net_cfg.compute_type != mstype.float32:
logger.warning('GPU only support fp32 temporarily, run with fp32.')
bert_net_cfg.compute_type = mstype.float32
else:
raise Exception("Target error, GPU or Ascend is supported.")
netwithloss = BertSquad(bert_net_cfg, True, 2, dropout_prob=0.1)
if args_opt.do_train.lower() == "true":
ds = create_squad_dataset(
batch_size=args_opt.train_batch_size,
repeat_count=1,
data_file_path=args_opt.train_data_file_path,
schema_file_path=args_opt.schema_file_path,
do_shuffle=(args_opt.train_data_shuffle.lower() == "true"))
do_train(ds, netwithloss, load_pretrain_checkpoint_path,
save_finetune_checkpoint_path, epoch_num)
if args_opt.do_eval.lower() == "true":
if save_finetune_checkpoint_path == "":
load_finetune_checkpoint_dir = _cur_dir
else:
load_finetune_checkpoint_dir = make_directory(
save_finetune_checkpoint_path)
load_finetune_checkpoint_path = LoadNewestCkpt(
load_finetune_checkpoint_dir, ds.get_dataset_size(), epoch_num,
"squad")
if args_opt.do_eval.lower() == "true":
from src import tokenization
from src.create_squad_data import read_squad_examples, convert_examples_to_features
from src.squad_get_predictions import write_predictions
from src.squad_postprocess import SQuad_postprocess
tokenizer = tokenization.FullTokenizer(
vocab_file=args_opt.vocab_file_path, do_lower_case=True)
eval_examples = read_squad_examples(args_opt.eval_json_path, False)
eval_features = convert_examples_to_features(
examples=eval_examples,
tokenizer=tokenizer,
max_seq_length=bert_net_cfg.seq_length,
doc_stride=128,
max_query_length=64,
is_training=False,
output_fn=None,
vocab_file=args_opt.vocab_file_path)
ds = create_squad_dataset(
batch_size=args_opt.eval_batch_size,
repeat_count=1,
data_file_path=eval_features,
schema_file_path=args_opt.schema_file_path,
is_training=False,
do_shuffle=(args_opt.eval_data_shuffle.lower() == "true"))
outputs = do_eval(ds, load_finetune_checkpoint_path,
args_opt.eval_batch_size)
all_predictions = write_predictions(eval_examples, eval_features,
outputs, 20, 30, True)
SQuad_postprocess(args_opt.eval_json_path,
all_predictions,
output_metrics="output.json")