issues
search
zinengtang
/
TVLT
PyTorch code for “TVLT: Textless Vision-Language Transformer” (NeurIPS 2022 Oral)
MIT License
120
stars
13
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
#17
saransh03sharma
opened
9 months ago
0
error in Demo_Video_Audio_MAE.ipynb opened in colab
#16
snapfinger
opened
1 year ago
0
VQAv2 finetuned checkpoint
#15
farisalasmary
opened
1 year ago
1
Finetuning for the custom dataset
#14
palashmoon
opened
1 year ago
0
about mosei
#13
LM-MSA
opened
1 year ago
0
Whether the text of MOSEI's text-based results comes from ASR or raw dataset?
#12
Yimi81
closed
1 year ago
0
Draw false video from batch
#11
G-JWLee
closed
1 year ago
1
inaccurate VQA score
#10
Park-ing-lot
opened
1 year ago
3
Finetuning for emotion analysis but nan output
#9
Changezi001
opened
1 year ago
3
Finetuning on MOSEI but with nan output
#8
BDHU
closed
1 year ago
4
CUDA memory error
#7
Park-ing-lot
closed
1 year ago
2
The question for cmumosei.
#6
AIXiaoBaiDemon
opened
1 year ago
4
In accurate test results for emotion classification
#5
Changezi001
closed
1 year ago
5
Downstream task Cosine scheduler
#4
G-JWLee
closed
1 year ago
7
Processing cmumosei dataset
#3
BDHU
closed
1 year ago
8
CMU-MOSEI valid test
#2
dori2063
closed
2 years ago
1
rawvideo_utils: cleanup & bugfix audio_to_tensor
#1
zijian-hu
closed
2 years ago
1