Akarsh

Updated the learn2learn "image_classification_imagenette_mini" example

9

## What does this PR do? There were some problems in the downloading of the dataset as well as defining the `ImageClassificationInputTransform`, for the `ImageClassificationData`, so I have remade the...

## 🚀 Feature Extending the idea of Question Answering to Visual Question Answering ### Motivation I was going through the [example](https://lightning-flash.readthedocs.io/en/latest/reference/question_answering.html) and was interested in using transformers for the purpose...

## What does this PR do? Fixes #1452 Currently, I was able to only find the changes in `flash/core/utilities/imports.py` ## Before submitting - [x] Was this **discussed/approved** via a Github...

# 🚀 Feature ## Motivation - Is currently the SOTA on VQA Model - Has a novel attention mechanism for taking the Image, Language and Spatial features for the purpose...

Downloading the Image for the whole dataset

22

Hi @furkanbiten, you have given the link for downloading the Raw OCR, however I am not able to download the corresponding images (not sure about how to go for it)....

Clarification regarding the implementation and training of LaTr

7

This thread contains the discussion of the implementation of LaTr with one of the authors of the same paper The earlier discussion with the first author is mentioned [here](https://github.com/uakarsh/latr/issues/2#issuecomment-1153231321)