- 发行说明
2023 年 2 月
在端点 + DocumentUnderstanding + 数据提取 ML 包中发布 | v23.2.0
新增功能和改进
A new version of the Out-of-the-box Pre-trained ML Packages (23.1.0) and their public endpoints has been released, now using cutting edge LayoutLM Transformers based architecture, which is more powerful and increases accuracy overall, especially on column fields (tables).
This improvement has made the Out-of-the-box Pre-trained ML Packages more powerful, meaning that you may experience longer latency for training and for predictions.
For all situations where latency is critical (e.g.: attended scenarios) we recommend deploying the models as ML Skills using a GPU.
We have improved how the scores are calculated after Training/Evaluation/Full pipelines to provide a separate score for each column field. Before this improvement, F1 scores were calculated as a whole, for all column fields taken together.
我们宣布即将移除模型评估中使用的手动编辑功能。单击此处可查看更多信息。
已知问题
The project import from AI Center is currently disabled. We are actively working on this and expect to have it reenabled by the end of March.
2023 年 5 月 8 日勘误
已知问题
Fatal Python error: Segmentation fault
。 在此错误修复之前,我们建议您使用 ML 包 v23.4。
2023 年 4 月 20 日勘误
所有管道的总分现在表示准确度,以前表示 F1 分数。为了保持向后兼容性,AI Center 中的评估工件仍同时包含准确度和 F1 分数。