AutoML文本分类的数据集导入错误 [英] dataset import error for AutoML text classification

问题描述

我试图将数据集导入AutoML NL文本分类.但是，Ui给我一个CSV文件中无效行的错误，错误详细信息:检测到错误:"FILE_TYPE_NOT_SUPPORTED"

I have trying to import dataset into AutoML NL Text Classification. However, the Ui gave me an error of Invalid row in CSV file , Error details: Error detected: "FILE_TYPE_NOT_SUPPORTED"

我正在上传csv文件，该怎么办?

I am uploading the csv file, what should I do?

推荐答案

请确保数据集中没有隐藏的引号.可以在"准备训练数据"页面上找到完整的要求.

Please make sure there is no hidden quotes in your dataset. Complete requirements can be found on "Preparing your training data" page.

.csv常见错误:

Common .csv errors:

• 在标签中使用Unicode字符.例如，不支持日语字符.
• 在标签中使用空格和非字母数字字符.
• 空行.
• 空列(带有两个连续逗号的行).
• 在包含逗号的嵌入式文本周围缺少引号.
• Cloud Storage文本路径的大小写不正确.
• 为文本文件配置了错误的访问控制.您的服务帐户应具有读取权限或更高的访问权限，或者文件必须是公开可读的.
• 对非文本文件(例如JPEG文件)的引用.同样，不是文本文件但已使用文本扩展名重命名的文件也会导致错误.
• 文本文件的URI指向与当前项目不同的存储桶. >>-仅可以访问项目存储区中的文件.
• 非CSV格式的文件.

• Using Unicode characters in labels. For example, Japanese characters are not supported.
• Using spaces and non-alphanumeric characters in labels.
• Empty lines.
• Empty columns (lines with two successive commas).
• Missing quotes around embedded text that includes commas.
• Incorrect capitalization of Cloud Storage text paths.
• Incorrect access control configured for your text files. Your service account should have read or greater access, or files must be publicly-readable.
• References to non-text files, such as JPEG files. Likewise, files that are not text files but that have been renamed with a text extension will cause an error.
• The URI of a text file points to a different bucket than the current project. > > - Only files in the project bucket can be accessed.
• Non-CSV-formatted files.

这篇关于AutoML文本分类的数据集导入错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！