Xiwen Li comments

Results 8 comments of


                                            Xiwen Li

ZeroDivisionError: float division by zero in loss function

I also got the same error when training on mugs_all.yaml. Here is the entire message. It looks like one of the mask is empty. `warning, empty mask b Traceback (most...

TypeError: Expected a Trimesh or a list, got a <class 'trimesh.scene.scene.Scene'>

> same problem, is this fixed? You can create a list to load all elements in the `trimesh.geometry.values() ` and add them into scene one by one

How to get a file similar to ava_categories_ratio.json

I don't have the exact answer. But I think AVA is multilabel dataset which mean each bounding box might have multiple predicted labels. As a result, we cannot just divide...

Train / Validation / Test splits for million song dataset

> @yiyiyi0817 don't know about those files specifically (@codyhesse and @SebastianLoef might know more), but we believe the splits used in CLMR were the ones by @keunwoochoi over in https://github.com/keunwoochoi/MSD_split_for_tagging...

Train / Validation / Test splits for million song dataset

> @lix4 it's on the mentioned repo - https://github.com/keunwoochoi/MSD_split_for_tagging I mean the original data files like "3/6/36122424.npy". Is there a place I can download it?

Train / Validation / Test splits for million song dataset

> you meant the audio files. sorry you should ask around people who might have them as the crawling API doesn't work anymore. it's very problematic that i even wrote...

Question about frame mAP evaluation

> Thanks for your awesome project. I want to evaluate the frame mAP performance as you offered in the paper. Could you please tell me which function is for frame...

LFB code?

Same question here.