This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"
I finetuned the model from epoch_36 to epoch_78.. I have 3 class border, borderless and cells..Using transfer learning from provided checkpoint 36 and fine tuning upto 78, i can accurately classify bordered and borderless table but model misses cells detection by 50%. I have trained on custom financial dataset 18k data samples... Can you provide some techniques inorder to detect cells accurately.. should i contime training few more epochs?? Should i tune some specific parameters so i can detect all cells???
I finetuned the model from epoch_36 to epoch_78.. I have 3 class border, borderless and cells..Using transfer learning from provided checkpoint 36 and fine tuning upto 78, i can accurately classify bordered and borderless table but model misses cells detection by 50%. I have trained on custom financial dataset 18k data samples... Can you provide some techniques inorder to detect cells accurately.. should i contime training few more epochs?? Should i tune some specific parameters so i can detect all cells???