issues
search
uakarsh
/
latr
Implementation of LaTr: Layout-aware transformer for scene-text VQA,a novel multimodal architecture for Scene Text Visual Question Answering (STVQA)
https://uakarsh.github.io/latr/
MIT License
52
stars
7
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
huggingface demo
#16
mxw20010804
opened
2 months ago
0
An error in dataset.py : create_features function
#15
HouTong-s
opened
1 year ago
0
Added the `requirements.txt` file for easy installation
#14
uakarsh
closed
1 year ago
0
eval_func
#13
tinaboya2023
opened
1 year ago
19
span masking
#12
jianglong-he-Infrrd
opened
1 year ago
1
How to evaluate by Average Normalized Levenshtein Similarity (ANLS)?
#11
kobrafarshidi
opened
1 year ago
1
error in max_step
#10
mohanades
opened
1 year ago
1
Question about prediction a sample
#9
kobrafarshidi
opened
1 year ago
2
Bump pillow from 7.1.2 to 9.3.0
#8
dependabot[bot]
closed
1 year ago
1
Questions about pretraining and fine tuning
#7
kobrafarshidi
opened
2 years ago
22
Error in use of your dataset textvqa
#6
kobrafarshidi
closed
2 years ago
4
error in loss.backward() project
#5
kobrafarshidi
closed
2 years ago
4
how to change dataser
#4
kobrafarshidi
closed
2 years ago
5
Clarification regarding the implementation and training of LaTr
#3
uakarsh
opened
2 years ago
7
The results without pre-training
#2
Gyann-z
opened
2 years ago
13
word embedding layer
#1
youngsheen
closed
2 years ago
3