gsrivas4

@Kerry-zzx @abhidipbhattacharyya were you able to get this mapping. I am also looking for the same, but it is difficult to get.

Actually with little more digging found the vocabulary here - https://github.com/peteanderson80/bottom-up-attention/tree/master/data/genome/1600-400-20.

@qin79 I could get class labels, bounding box and features using this repo - https://github.com/airsplay/py-bottom-up-attention.

@violetteshev I am planning to use your repo to get the bottom up features. My machine has CUDA 10.1 and pytorch version 1.5.0. Can you suggest what issues might occur,...

The [TID2013 paper](https://www.sciencedirect.com/science/article/pii/S0923596514001490) mentions, in section 4.1 that the range of scores is 0 to 9. If the model was trained on the ground truth scores from TID, then the...

@vincentlux I am planning to use the repo that you have mentioned above - https://github.com/airsplay/py-bottom-up-attention, to generate features another dataset I have been working on. I was wondering if you...

When you mention under default settings, does that mean default settings for Transformer and can it be an issue for LSTMs etc.? I understand that the using `sort_pack_padded_sequence` and `pad_unsort_packed_sequence`...

I tried that. This gave another error `TypeError: memoryview: a bytes-like object is required, not 'str'` on this line - https://github.com/ruotianluo/self-critical.pytorch/blob/master/scripts/make_bu_data.py#L44-L45.

Both `ascii` and `utf-8` encoding work. How would I know which one gives correct output files? I guess, one way to check is see check the evaluation results generated by...

I checked the output of item[field] for both the encodings, 'utf-8' and 'ascii', and they give the same result arrays.