无法开始在Web UI上训练我的GCP AutoML实体提取模型 [英] Unable to start training my GCP AutoML Entity Extraction model on Web UI

问题描述

我正在尝试使用AutoML Web UI训练我的第一个GCP AutoML实体提取模型.

I am trying to train my first GCP AutoML Entity Extraction model using AutoML Web UI.

我加载并注释了带有9个标签的74个PDF(6页PDF)(请参阅GCP AutoML实体提取).看来我尊重训练，验证和测试集的最少10条注释.但是，我无法单击开始培训"(Web UI上的灰色按钮).GCP AutoML Web UI没有给出指示.

I loaded and annotated 74 PDFs (6-pages PDF) with 9 labels (see Screenshot of GCP AutoML Entity Extraction). It seems that I respected the 10 annotations minimum for both train, validation and test sets. Nevertheless, I am unable to click on Start Training (greyed-out button on Web UI). No indication is given by the GCP AutoML Web UI.

任何帮助将不胜感激.谢谢.

Any help would be greatly appreciated. Thanks.

我忘了提到数据集位于欧盟.

I forgot to mention that the dataset is located in European Union.

推荐答案

我在支持人员的陪同下聊天，这是一个已知问题"，-最小数量的每个标签培训项目"是100.是的，如果将其反映在用户界面中并且他们知道这一点，将很有用.

I chatted with support and this is a "known issue" - the minimum number of "Training items per label" is 100. Yes, it would be useful if this was reflected in the UI, and they know this.

来源: https://cloud.google.com/natural-language/automl/quotas#limits

这篇关于无法开始在Web UI上训练我的GCP AutoML实体提取模型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！