Muhammad Irfan

bump

I have run the `predict.py` script successfully. But it seems there is a bug in the predictor. Here are parameters. ```shell --data_path /home/irfan/PycharmProjects/disambiguate/model/model_wsd_train_sc_wngt_dev_random4000_clear_compress_bert_large_cased_transformer_2048_single --weights /home/irfan/PycharmProjects/disambiguate/model/model_wsd_train_sc_wngt_dev_random4000_clear_compress_bert_large_cased_transformer_2048_single/model_weights_wsd0 ``` But when I type...

@lihka1 it depends on the alphabet you used for training the model. Here you have `.` but in alphabet its not there so it will not correct this word.

It seems InvoiceNet cant handle the tables for example.  How can we extract the items from the table as the criteria of using the custom field take only a...

Nope. Use something else like yolo. I did solve the issue using Yolo3.

https://github.com/ultralytics/yolov3

I labeled the dateset. Here are the results using yolo and then train a yolo v3 model. 

Why not. Yolo can solve the table issue. Just label the table and after detection use ocr to extract text.

I have done similar to this. You need to label columns with yolo. Detect and OCR. You need more data to get better accuracy. Around 50 samples of a single...

 Like this.