执行run_classifier_infer遇到问题

[LiXuefeng2020ai]

执行run_classifier_infer遇到问题

Traceback (most recent call last):
  File "inference/run_classifier_infer.py", line 142, in <module>
    main()
  File "inference/run_classifier_infer.py", line 101, in main
    dataset = read_dataset(args, args.test_path)
  File "inference/run_classifier_infer.py", line 46, in read_dataset
    text_a = line[columns["text_a"]]
KeyError: 'text_a'

[ydli-ai]

在数据的第一行增加一个 text_a 的表头，可以参考示例数据集的格式

---

发件人: LiXuefeng2020ai @.> 发送时间: Wednesday, May 11, 2022 2:30:33 PM 收件人: dbiir/UER-py @.> 抄送: Subscribed @.***> 主题: [dbiir/UER-py] 执行run_classifier_infer遇到问题 (Issue #310)

执行run_classifier_infer遇到问题

Traceback (most recent call last):

File "inference/run_classifier_infer.py", line 142, in

main()

File "inference/run_classifier_infer.py", line 101, in main

dataset = read_dataset(args, args.test_path)

File "inference/run_classifier_infer.py", line 46, in read_dataset

text_a = line[columns["text_a"]]

KeyError: 'text_a'

― Reply to this email directly, view it on GitHubhttps://github.com/dbiir/UER-py/issues/310, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AE3SPV45GN5DRSN6XDTG46TVJNHYTANCNFSM5VTZH4LA. You are receiving this because you are subscribed to this thread.Message ID: @.***>

[Embedding]

可能是文件编码的问题 比如推理UTF-8 with BOM编码的文件会导致上面的问题，即使第一行有text_a