issues
search
salesforce
/
ALBEF
Code for ALBEF: a new vision-language pre-training method
BSD 3-Clause "New" or "Revised" License
1.57k
stars
199
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Missing text-only Transformer in visualization notebook
#95
BennoKrojer
opened
2 years ago
4
Questions about the results of NLVR2
#94
junyubi
opened
2 years ago
0
RuntimeError: invalid multinomial distribution (sum of probabilities <= 0)
#93
yirutsai
opened
2 years ago
5
Training behavior on 16 gpus
#92
zhaohengz
opened
2 years ago
2
Question about VQA answer tokenizer
#91
katrina433
closed
2 years ago
2
About VQA mlm loss
#90
katrina433
closed
2 years ago
1
Zero-shot evaluation results about Pretrain models
#89
wjxzju
opened
2 years ago
1
Only inference not finetune using VQA
#88
SKBL5694
opened
2 years ago
0
About generating VQA test result files
#87
yang178908
opened
2 years ago
2
About answer_ List modification
#86
Xjmengnieer
opened
2 years ago
1
Questions about the epochs of pre-training ?
#85
Fly2flies
closed
2 years ago
2
Questions about visual grounding
#84
jaeseokbyun
opened
2 years ago
2
Whole sentence visualization in Fig.4 and Fig10
#83
haoshuai714
closed
2 years ago
4
Pre-training Image-Text Matching
#82
xiezhiweihk
closed
2 years ago
1
Pretraining epochs
#81
haoshuai714
closed
2 years ago
0
About license
#80
WangWenhao0716
closed
2 years ago
2
IncompatibleKeys
#79
mzolfaghari
opened
2 years ago
2
Finetune for image-text retrieval task on COCO
#78
yxoh
opened
2 years ago
1
Pre-training on custom datasets
#77
xiezhiweihk
closed
2 years ago
2
Question about initialising Bert while pretraining
#76
MiraclesinWang
closed
2 years ago
3
Why get_special_tokens_mask appending a [1] at the end while build_inputs_with_special_tokens does not append a [SEP] at the end for a single input sequence ?
#75
zhihuacc
opened
2 years ago
3
Image-Text Retrieval Task, ITC score for ranking
#74
yxoh
closed
2 years ago
6
RefCOCO+ Result
#73
haoshuai714
closed
2 years ago
2
Caption Dataset Class Bug
#72
nehad-procogia
opened
2 years ago
0
Result worse than it in the paper
#71
liuuzexiang
closed
2 years ago
10
VQA dataset keys don't match code
#70
shankyemcee
opened
2 years ago
4
Test On Visual Grounding on RefCOCO+ Task
#69
haoshuai714
closed
2 years ago
2
segmentation layer
#68
chaochen99
opened
2 years ago
1
Question about nlvr checkpoint
#67
g25h1
closed
2 years ago
2
GPU memory rises continuously
#66
yuanrr
opened
2 years ago
1
Apex
#65
dw-dengwei
closed
2 years ago
1
obout some json files
#64
TungWg
closed
2 years ago
4
Add Docker environment & web demo
#63
chenxwh
closed
2 years ago
1
Retrieval result varies on multi-gpu distributed training
#62
averyma
opened
2 years ago
1
Which layers of BERT are used for MLM Loss?
#61
rakeshchada
opened
2 years ago
3
How much memory is needed for pre-training
#60
2292384454
opened
2 years ago
2
grounding results
#59
ziyanyang
closed
2 years ago
2
about MLM softlabel implementation
#58
zhezh
opened
2 years ago
3
How to get VQA result?
#57
haoshuai714
closed
2 years ago
3
Visual Entailment dataset?
#56
haoshuai714
closed
2 years ago
1
4M Pre-trained checkpoint
#55
haoshuai714
closed
2 years ago
2
grad-cam code
#54
ziyanyang
closed
2 years ago
2
question about ITM loss
#53
Qiulin-W
closed
2 years ago
7
what is the reasonable magnitude of mlm_loss after pretraining?
#52
Qiulin-W
closed
2 years ago
2
Visual Grounding, Whole sentence visualization in Fig.4
#51
zzzzzigzag
closed
2 years ago
2
Questions about Visual Grounding checkpoint and visualization
#50
zzzzzigzag
closed
2 years ago
5
pretrain dataset raw images
#49
lireagan
closed
2 years ago
1
test in VQA dataset
#48
haoshuai714
closed
2 years ago
7
Pre-trained checkpoint
#47
haoshuai714
closed
2 years ago
2
NCCL problems of pretrain
#46
Junjie-Ye
closed
2 years ago
3
Previous
Next