search

aws-samples / amazon-comprehend-semi-structured-documents-annotation-tools

Other
24 stars 15 forks source link

Will this now support TIFF files as well as PDF #5

Closed tomhands1 closed 2 years ago

tomhands1 commented 2 years ago

Now that AWS Textract has added support for tiff files analysis as well as PDF's via the AnalyzeDocument method https://aws.amazon.com/about-aws/whats-new/2021/10/amazon-textract-tiff-asynchronous-receipts-invoices/ would this document annotation tool be able to be used for those file types too?

yinxiaoz-amzn commented 2 years ago

Hi, currently, the image format is not supported by this tool, only PDF format is accepted. But we can take it as the feature request. in the meanwhile, a workaround is to convert image format into PDF format

hs-afactory commented 2 years ago

Hi Team, I am getting error "ModuleNotFoundError: No module named 'utils.s3_helper'" While running "comprehend-ssie-annotation-tool-cli.py" I am not able to find dependency. I want to annotate pdf to classify type of pdf. Recured manifest file to be generate for ML model testing.

dnlen commented 2 years ago

The latest comment has a separate issue open for it. Closing this issue.

harishbattula commented 1 year ago

Hi, currently, the image format is not supported by this tool, only PDF format is accepted. But we can take it as the feature request. in the meanwhile, a workaround is to convert image format into PDF format

What file formats it supports for inference??