issues
search
cshizhe
/
VLN-HAMT
Official implementation of History Aware Multimodal Transformer for Vision-and-Language Navigation (NeurIPS'21).
MIT License
99
stars
12
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
The test set result output is missing during the inference phase
#18
jj023721
closed
2 weeks ago
0
Can you please provide the ckpts of r2r-last, r2r-back and r4r?
#17
Hoyyyaard
opened
4 months ago
0
Memory leak during newEpisode in data pre-processing
#16
GengzeZhou
opened
1 year ago
3
The issues about the performance of two-Stage pretraining model
#15
imzhangsheng
opened
1 year ago
2
About the second stage is training ViT in an end-to-end manner.
#14
yhl2018
opened
1 year ago
0
About the pre-training problems
#13
imzhangsheng
closed
1 year ago
1
Suggest to loosen the dependency on networkx
#12
Agnes-U
opened
1 year ago
0
Multi-node training
#11
qizhust
closed
2 years ago
1
provided features differs from extracted features
#9
wz0919
closed
2 years ago
2
Instructions to obtain 'panoimages.lmdb'
#8
zdou0830
closed
1 year ago
1
Question about the version of CLIP used in RxR.
#7
MarSaKi
closed
2 years ago
1
Could you sepecify the models that can reproduce the reported results?
#6
Xin-Ye-1
closed
2 years ago
1
About the e2e trained ViT model
#5
alloldman
closed
1 year ago
1
Matterport3D simulators
#4
diaoyudiaochan
opened
2 years ago
0
Questions about ViT end2end training
#3
jialuli-luka
closed
2 years ago
4
Questions about pre-trained model
#2
jialuli-luka
closed
2 years ago
1
Could you please share the running scripts for IL+RL training from scratch?
#1
Jackie-Chou
opened
2 years ago
3