Arnau Castellano

Is there any way to solve this issue?

> Hi, > The EasyOCR is a four-step process, 1) pre-processing, 2) detection, 3) classification, 4) post-processing > I moved steps 2 and 3 to Tirton and 1 and 4...

@apsdehal @RishabhMaheshwary @RishabhMaheshwary Any updates?

Hi! This worked for me: I created a file in the root mmf directory called `my_run.py` containing the following: ```python from mmf_cli.run import run from mmf_cli.predict import predict opts =...

Any updates?

looking forward to the fine-tuning code for VQA as well.