Issues
- 1
RuntimeError: CUDA error: no kernel image is available for execution on the device
#22 opened by mtkinit - 1
Is it possible to share the F1 score or accuracy of pre-training the models in their control setting in the image sentence alignment objective?
#21 opened by kaiweicen - 1
h5 files
#20 opened by PhehJingJie - 1
- 2
visual location encoding in UNITER
#18 opened by PaulLerner - 2
multiple GPUS
#17 opened by nooralahzadeh - 3
vg-gqa_boxes36.lmdb file
#16 opened by nooralahzadeh - 6
Alternative Download Link for Preprocessed data
#14 opened by sh0416 - 6
- 1
Experienced system hanging?
#12 opened by juliuswang0728 - 1
Plans to add ERNIE-ViL?
#11 opened by VSJMilewski - 7
Miscalculated GQA score?
#13 opened by eladsegal - 2
- 6
Is it possible to provide a pretrained LXMERT model and fine-tune it with your code on RefCOCO?
#6 opened by yonatanbitton - 2
Is it possible to release pretrained model weights (without downstream task fine-tuned)?
#9 opened by Mallory24 - 2
Finetuning models on SNLI-VE
#7 opened by jaweriah - 0
Resume Training
#8 opened by jaweriah - 1
Paths to Test checkpoints
#5 opened by darthgera123 - 2
- 7
- 3
LMDB file download
#2 opened by darthgera123 - 1
When will the code be available?
#1 opened by valuefish