search

brightmart / text_classification

all kinds of text classification models and more with deep learning
MIT License
7.83k stars 2.57k forks source link

能提供a02_TextCNN完整的数据吗？ #67

Closed kevinsay closed 5 years ago

kevinsay commented 6 years ago

create_voabulary_label_sorted.ended.len of vocabulary_label: 1999 Traceback (most recent call last): File "p7_TextCNN_predict.py", line 42, in questionid_question_lists = load_final_test_data(FLAGS.predict_source_file) File "/home/text_classification-master/a02_TextCNN/other_experiement/data_util_zhihu.py", line 411, in load_final_test_data final_test_file_predict_object = codecs.open(file_path, 'r', 'utf8') File "/usr/lib/python3.5/codecs.py", line 895, in open file = builtins.open(filename, mode, buffering) FileNotFoundError: [Errno 2] No such file or directory: 'test-zhihu-forpredict-title-desc-v6.txt'

Amanda2024 commented 5 years ago

为什么单标签的准确率只有百分之20左右 啊，，，怎么这么低啊

brightmart commented 5 years ago

which data set you are using? if you use default dataset, it has 1999 tables, with few sample data. you can use your own data,.

发件人: RuanJingqing notifications@github.com 发送时间: 2018年10月25日 9:24 收件人: brightmart/text_classification 抄送: Subscribed 主题: Re: [brightmart/text_classification] 能提供a02_TextCNN完整的数据吗？ (#67)

为什么单标签的准确率只有百分之20左右 啊，，，怎么这么低啊

― You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/brightmart/text_classification/issues/67#issuecomment-432881384, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ASuYMPV-9VhqnNCTcQim0hnVpC8vDZW5ks5uoRLogaJpZM4U-_-T.

brightmart commented 5 years ago

re-generated data, and save as cached file, available to download. check this session in README.md:

Sample data: cached file