Dan Kondratyuk

Sorry for the late reply. I might have to come back to you on answering the specific questions, as it's been a long time since I touched this code. As...

To navigate between levels, you need to swipe the center of the screen up or down to scroll. This is meant to be run on mobile touch interfaces. I would...

@Carina02 Thanks for letting me know that you now have an official repository. I'll update my README so that others may find it.

I was also puzzled by the discrepancy, but I didn't find an answer yet. There could be a range of factors, but the most likely culprit is how the differential...

@Carina02 If you have time, you could experiment with this hypothesis. I think it would be simple to import and reload each image with opencv during preprocessing. Did you test...

@Carina02 Thanks for the update! Glad you were able to find the cause of the discrepancy.

`imagenet_urls.txt` is just a sample file with some example URLs and is by no means finished or ideal for testing. 1. About the URLs being invalid: yes, this is a...

Finding a good set of URLs with valid labels would be necessary. Unfortunately, I have not found any easy automated tools to do this, so it needs some manual work....

That's a good idea. Now that I see that Hugggingface has added support for it, it should be straightforward to add support here. I might get around to it, but...

The first thing to do would be to add the latest `transformers` release to `requirements.txt` which has XLM RoBERTa [here](https://github.com/huggingface/transformers/blob/master/src/transformers/tokenization_xlm_roberta.py) and [here](https://github.com/huggingface/transformers/blob/master/src/transformers/modeling_xlm_roberta.py). Then it should be imported into [`udify/modules/bert_pretrained.py`](https://github.com/Hyperparticle/udify/blob/master/udify/modules/bert_pretrained.py#L15) and...