检测不正确的自定义模型 - 在表单识别器中撰写模型
我创建了一个包含多个自定义模型的组合模型。对于一份本应使用模型 A 进行分析的特定文档，最终使用了错误的模型 B。
这里有一些具体需要了解的内容：
- 申请可以完全填写或部分填写（因此我将两者都添加到我的训练集中）
- 讨论中的两个模型都在格式完全不同的申请表上进行训练
观察：
- 如果测试文档在模型 A（正确模型）上测试，则置信度为 80%
- 如果测试文档在 compose 模型上测试，则采用 modelB 进行分析，此时 docType 置信度为 21%
Q1 ）组合模型不是应该用最佳拟合模型进行分析吗？在这种情况下，模型 A 最适合。但选择了模型B。
Q2) 构建大量模型（例如 40 个范围内）时，训练的最佳实践是什么
Q3) 如何解决此类问题？
I have created a compose model with multiple custom models. For one specific document where it was supposed to use model A for analysis, ends up using model B which is incorrect.
Here are few specific to know:
- Applications could be completely filled or partially filled (So I added both to my training set)
- Both the models in discussion are trained on application form totally different in format
Observations:
- If the test document is tested on model A(correct model), the confidence is 80%
- If the test document is tested on compose model, modelB is taken up for analyze and docType Confidence is 21% in this case
Q1) Isn't compose model supposed to perform analyze with best fit model? In this case model A is best fit. But model B is selected.
Q2) What's the best practices for training when composing huge set of models (say in the range of 40)
Q3) How can issues like this be fixed?
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（2）
组合模型选择最适合的模型来分析文档。模型 A 和模型 B 中的文档结构相似吗？如果文档相似，您可能会获得更高的准确度，为两个文档创建单个模型。尝试将模型 B 中的文档添加到模型 A 的训练集中，并在没有模型 B 的情况下进行组合，看看这是否会提高组合模型的准确性。
Composed model selects the best fit model to analyze the document. Are documents in Model A and Model B similar in structure ? If the documents are similar you might get higher accuracy creating a single model for both documents. Try adding documents from model B into the training set of model A and compose without Model B and see if that improves the accuracy of the composed model.
我收到了微软团队对此的回复，The way compose model work似乎在3.0版本上得到了改进。我在 Form Recognizer Studio (3.0) 上尝试使用完全相同的训练数据，并且撰写功能按预期工作！
I received a response from Microsoft team on this, The way compose model works seems to be refined on 3.0 version. I tried with exact same training data on Form Recognizer Studio (3.0) and the compose feature is working as expected!