[英]Fine tuning on either Google Cloud Vision, Microsoft Azure Computer Vision API or Amazon Text Extract
I need to transcribe a large number of Handwritten documents.我需要转录大量手写文件。 I tried to use cloud services from either Google, Amazon, and Microsoft.我尝试使用谷歌、亚马逊和微软的云服务。 Namely:即:
Unfortunately, none of them achieved good enough results.不幸的是,他们都没有取得足够好的结果。 I suspect it is because my documents have a weird handwriting style, and as a result, the networks struggle a lot.我怀疑这是因为我的文档有一种奇怪的笔迹风格,因此,网络非常困难。 I searched whether I could fine-tune (with manually transcribed data), but I have not found anything online, so as a last resort, I ask here.我搜索了是否可以微调(使用手动转录的数据),但我没有在网上找到任何东西,所以作为最后的手段,我在这里问。
If it is possible to fine-tune one of these models, could you please point me some resources?如果可以对其中一个模型进行微调,能否请您指出一些资源?
You are correct, with Azure Cognitive Services with Computer Vision you cannot upload your own data to train the API to recognise the handwriting in your documents I'm afraid.你是对的,使用 Azure 认知服务和计算机视觉你不能上传你自己的数据来训练 API 来识别你文档中的笔迹恐怕。 I can't comment on the other offerings from AWS and Google I'm afraid, but certainly not for Azure.恐怕我无法评论 AWS 和 Google 的其他产品,但肯定不是 Azure。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.