Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

modify for bert 310infer on r1.3

This commit is contained in:
郑彬 2021-07-12 14:40:24 +08:00
parent cd2d2bef0a
commit 3309c6159d
4 changed files with 30 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
model_zoo/official/nlp/bert/postprocess.py
View File

@ -21,11 +21,31 @@ import os
import argparse
import numpy as np
from mindspore import Tensor
from src.model_utils.config import bert_net_cfg
from src.assessment_method import Accuracy, F1, MCC, Spearman_Correlation
from run_ner import eval_result_print
def eval_result_print(assessment_method_="accuracy", callback_=None):
"""print eval result"""
if assessment_method_ == "accuracy":
print("acc_num {} , total_num {}, accuracy {:.6f}".format(callback_.acc_num, callback_.total_num,
callback_.acc_num / callback_.total_num))
elif assessment_method_ == "bf1":
print("Precision {:.6f} ".format(callback_.TP / (callback_.TP + callback_.FP)))
print("Recall {:.6f} ".format(callback_.TP / (callback_.TP + callback_.FN)))
print("F1 {:.6f} ".format(2 * callback_.TP / (2 * callback_.TP + callback_.FP + callback_.FN)))
elif assessment_method_ == "mf1":
print("F1 {:.6f} ".format(callback_.eval()[0]))
elif assessment_method_ == "mcc":
print("MCC {:.6f} ".format(callback_.cal()))
elif assessment_method_ == "spearman_correlation":
print("Spearman Correlation is {:.6f} ".format(callback_.cal()[0]))
else:
raise ValueError("Assessment method not supported, support: [accuracy, f1, mcc, spearman_correlation]")
parser = argparse.ArgumentParser(description="postprocess")
parser.add_argument("--seq_length", type=int, default=128, help="seq_length, default is 128. You can get this value "
"through the relevant'*.yaml' filer")
parser.add_argument("--batch_size", type=int, default=1, help="Eval batch size, default is 1")
parser.add_argument("--label_dir", type=str, default="", help="label data dir")
parser.add_argument("--assessment_method", type=str, default="BF1", choices=["BF1", "clue_benchmark", "MF1"],
@ -58,21 +78,21 @@ if __name__ == "__main__":
for f in file_name:
if use_crf.lower() == "true":
logits = ()
for j in range(bert_net_cfg.seq_length):
for j in range(args.seq_length):
f_name = f.split('.')[0] + '_' + str(j) + '.bin'
data_tmp = np.fromfile(os.path.join(args.result_dir, f_name), np.int32)
data_tmp = data_tmp.reshape(args.batch_size, num_class + 2)
logits += ((Tensor(data_tmp),),)
f_name = f.split('.')[0] + '_' + str(bert_net_cfg.seq_length) + '.bin'
f_name = f.split('.')[0] + '_' + str(args.seq_length) + '.bin'
data_tmp = np.fromfile(os.path.join(args.result_dir, f_name), np.int32).tolist()
data_tmp = Tensor(data_tmp)
logits = (logits, data_tmp)
else:
f_name = os.path.join(args.result_dir, f.split('.')[0] + '_0.bin')
logits = np.fromfile(f_name, np.float32).reshape(bert_net_cfg.seq_length * args.batch_size, num_class)
logits = np.fromfile(f_name, np.float32).reshape(args.seq_length * args.batch_size, num_class)
logits = Tensor(logits)
label_ids = np.fromfile(os.path.join(args.label_dir, f), np.int32)
label_ids = Tensor(label_ids.reshape(args.batch_size, bert_net_cfg.seq_length))
label_ids = Tensor(label_ids.reshape(args.batch_size, args.seq_length))
callback.update(logits, label_ids)
print("==============================================================")

2
model_zoo/official/nlp/bert/pretrain_config.yaml
View File

@ -14,7 +14,7 @@ enable_profiling: False
# ==============================================================================
description: 'run_pretrain'
distribute: 'false'
epoch_size: 1
epoch_size: 40
device_id: 0
device_num: 1
enable_save_ckpt: 'true'

2
model_zoo/official/nlp/bert/run_pretrain.py
View File

@ -196,7 +196,7 @@ def run_pretrain():
cfg.save_checkpoint_steps *= cfg.accumulation_steps
logger.info("save checkpoint steps: {}".format(cfg.save_checkpoint_steps))
ds = create_bert_dataset(device_num, rank, cfg.do_shuffle, cfg.data_dir, cfg.schema_dir)
ds = create_bert_dataset(device_num, rank, cfg.do_shuffle, cfg.data_dir, cfg.schema_dir, cfg.batch_size)
net_with_loss = BertNetworkWithLoss(bert_net_cfg, True)
new_repeat_count = cfg.epoch_size * ds.get_dataset_size() // cfg.data_sink_steps

5
model_zoo/official/nlp/bert/src/dataset.py
View File

@ -20,10 +20,9 @@ import mindspore.common.dtype as mstype
import mindspore.dataset as ds
import mindspore.dataset.transforms.c_transforms as C
from mindspore import log as logger
from .model_utils.config import config as cfg
def create_bert_dataset(device_num=1, rank=0, do_shuffle="true", data_dir=None, schema_dir=None):
def create_bert_dataset(device_num=1, rank=0, do_shuffle="true", data_dir=None, schema_dir=None, batch_size=32):
"""create train dataset"""
# apply repeat operations
files = os.listdir(data_dir)
@ -46,7 +45,7 @@ def create_bert_dataset(device_num=1, rank=0, do_shuffle="true", data_dir=None,
data_set = data_set.map(operations=type_cast_op, input_columns="input_mask")
data_set = data_set.map(operations=type_cast_op, input_columns="input_ids")
# apply batch operations
data_set = data_set.batch(cfg.batch_size, drop_remainder=True)
data_set = data_set.batch(batch_size, drop_remainder=True)
logger.info("data size: {}".format(data_set.get_dataset_size()))
logger.info("repeat count: {}".format(data_set.get_repeat_count()))
return data_set