Akarsh

Thank you for your detailed answer, a lot of things got clear, and yes you are right, I would be making a new issue, linking it with this issue's discussion....

Hi @mohanades, I have realized some time back that, I have prepared the task in wrong way. So, here is what I have done I have tokenized the answers and...

Hi @kobrafarshidi, much sorry for late reply. Can you refer to this [thread](https://github.com/uakarsh/latr/issues/13#issuecomment-1488174690), and let me know if you still have doubt regarding the same.

Yep that is right, I should have done that earlier, but I was not knowing that earlier. Am just reflecting that from sometime back, so would do that soon.

There is a small mistake in the `predict_step` in the LatrForVQA class, and that is torch.max returns two values values, and indices, so you can fix the problem in two...

Hi @kobrafarshidi, all the answers would be related to the notebook `LaTr TextVQA Training with WandB`. 1. Actually, I focused more on the fine-tuning part/ training from scratch on a...

Hi there, 1. For the connection between the **Pre-training** and **Fine-tuning**, you can visit at this [link](https://github.com/uakarsh/latr/blob/a72a2ce299ee816c14b1af32058986c2b4c15c91/src/latr/modeling.py#L81). It simply goes that, if you have the initial weights trained, you can...

Hi there, 1. Actually in the pre-training part, I took a sample dataset, and hence the definition between the pre-training and fine-tuning code differs. The simplest way to use the...

Hi, In the first question, I don't think you need to find anything, you can download the IDL dataset, and then take reference to the code of pretraining for extracting...

Hi, I am not able to open the link. But, I think the essence would be to write a function, which can read the bounding boxes, and words for a...