Issues
- 0
Docker extract features error
#121 opened by cmcv2022 - 0
FileNotFoundError: [Errno 2] No such file or directory: '/hy-tmp/lxmert/data/vqa/valid.json'
#120 opened by nameyun - 0
Corrupt VQA dataset from the source provided
#119 opened by omm-prakash - 0
Error in fine-tuning GQA for large datasets
#118 opened by zilxv - 0
Labels
#116 opened by 25icecreamflavors - 2
- 0
- 1
Use of --qaSets parameter
#99 opened by aurooj - 4
training killed while loading image features
#98 opened by Youngju-Na - 0
- 0
filtering raw dataset in to get tiny dataset
#113 opened by samarIbrahem - 0
Pre-training mission error
#112 opened by MaxwellZYD - 0
Fine-tuning VQA on multiple gpus
#111 opened by simplelifetime - 0
Get predictions for batches
#110 opened by 25icecreamflavors - 12
The URLs are not accessable
#108 opened by BierOne - 1
binascii.Error: Incorrect padding
#101 opened by alice-cool - 0
No problem
#109 opened by alice-cool - 11
Split .tsv files
#79 opened by yikuan8 - 0
- 2
validation score of VQA
#106 opened by Yucheng-Han - 2
Relation between `lxrt.entry.LXRTEncoder` and `lxrt.modeling.LXRTEncoder`.
#92 opened by yezhengli-Mr9 - 0
why use tsv?
#105 opened by Yucheng-Han - 0
Training is stuck
#104 opened by lhlm1994 - 1
Why having a self-attn after cross_attn
#102 opened by LeungWaiHo - 0
np.all(feature == 0) is True, why
#103 opened by Yinhance - 0
finetun VQA
#100 opened by 1144181135 - 0
question on faster r-cnn feature extraction
#97 opened by theaitetus - 18
Bad performance of NLVR2.
#84 opened by yangxuntu - 0
Some question about nlvr
#96 opened by haoopan - 0
How to extract gqa_testdev_obj36.tsv feature?
#95 opened by yangxuntu - 2
- 0
- 0
- 1
How to get the language-only result?
#82 opened by weiwenlan - 3
- 1
object/attr prediction not masked
#90 opened by zhmd - 3
Using LXMERT for image captioning
#86 opened by freeIsa - 0
In eval mode, the values are equal.
#88 opened by Tramac - 1
- 0
Best pretrained model
#83 opened by violetteshev - 6
Not able to reproduce GQA(Train + BERT) 56.2
#80 opened by yix081 - 1
- 3
relationship between BatchSize and LR?
#77 opened by XChuanLee - 1
Freeze the model
#78 opened by titaiwangms - 0
PreTrain + BERT
#76 opened by Muennighoff - 2
VQA dataset
#75 opened by deepaknlp - 1
- 0
Class attribute of image features
#73 opened by Kerry-zzx - 1
Can I use -load_lxmert instead of -load_lxmert_qa when fine-tuning the VQA model?
#72 opened by yikuan8 - 0
VQA: Split-wise result during each epoch
#71 opened by gkv91