wehub-resource-sync
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
# Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import paddle
|
|
|
|
|
|
def create_dataloader(dataset, mode="train", batch_size=1, batchify_fn=None, trans_fn=None):
|
|
if trans_fn:
|
|
dataset = dataset.map(trans_fn)
|
|
|
|
shuffle = True if mode == "train" else False
|
|
if mode == "train":
|
|
batch_sampler = paddle.io.DistributedBatchSampler(dataset, batch_size=batch_size, shuffle=shuffle)
|
|
else:
|
|
batch_sampler = paddle.io.BatchSampler(dataset, batch_size=batch_size, shuffle=shuffle)
|
|
|
|
return paddle.io.DataLoader(dataset=dataset, batch_sampler=batch_sampler, collate_fn=batchify_fn, return_list=True)
|
|
|
|
|
|
def read_text_pair(data_path):
|
|
"""Reads data."""
|
|
with open(data_path, "r", encoding="utf-8") as f:
|
|
for line in f:
|
|
data = line.rstrip().split("\t")
|
|
if len(data) != 2:
|
|
continue
|
|
yield {"query": data[0], "title": data[1]}
|
|
|
|
|
|
def convert_example(example, tokenizer, max_seq_length=512, phase="train"):
|
|
|
|
query, title = example["query"], example["title"]
|
|
|
|
query_encoded_inputs = tokenizer(text=query, max_seq_len=max_seq_length)
|
|
query_input_ids = query_encoded_inputs["input_ids"]
|
|
query_token_type_ids = query_encoded_inputs["token_type_ids"]
|
|
title_encoded_inputs = tokenizer(text=title, max_seq_len=max_seq_length)
|
|
|
|
title_input_ids = title_encoded_inputs["input_ids"]
|
|
title_token_type_ids = title_encoded_inputs["token_type_ids"]
|
|
|
|
return query_input_ids, query_token_type_ids, title_input_ids, title_token_type_ids
|