Thomas Delteil

@techietrader, sorry I missed that question: yes you can easily pick which layer you want. Try to do: ``` print(net) ``` you should see every layer of the network then...

Hi @kapilt, any update on this PR ? It seems to contains lots of bug fixes that would be very much appreciated

I confirm this is still happening

@douglas125 @aakashpatel25 you can use a custom transform function on your dataset. ```python max_len = max([len(array) for array in batch_test]) def transform(x1, x2): x1_ = np.zeros(max_len) x2_ = np.zeros(max_len) x1_[:len(x1)]...

- Blocks should be ordered by geometry y-axis by default, if that's not the case somewhere please file a bug - We could add a helper function on the page...

### Table merging in pandas: [multipage.pdf](https://github.com/aws-samples/amazon-textract-textractor/files/10864129/multipage.pdf) ```python from textractor import Textractor from textractor.data.constants import TextractFeatures extractor = Textractor(profile_name="default") document1 = extractor.start_document_analysis( file_source='./multipage.pdf', features=[TextractFeatures.TABLES], s3_upload_path='s3://textractor-tests/debug/', s3_output_path='s3://textractor-tests/debug/', save_image=True ) df1 = document1.tables[0].to_pandas(use_columns=True)...

Column header visualization at the table level and `.is_column_header` have been added at the cell level. `.ocr_confidence` has been added to the KV element.

The ordering is very basic for now, it is based on the y coordinate of the boxes.

I think here what we want is actually to parse the document and recreate the API response from it.

You are right this seems to be a left-over from a previous implementaiton. The best way to pass multiple PIL images would simply be to use a for-loop and the...