Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / GenjiB/LAVISH issues and pull requests
#24 - Need few more details to debug the code for my task
Issue -
State: open - Opened by praveena2j 5 months ago
#23 - The output of vision transformers models are Nans
Issue -
State: open - Opened by praveena2j 7 months ago
#22 - How many gpu days does the training procedure of AVE take?
Issue -
State: open - Opened by laulliam 8 months ago
#21 - About performance in AVQA
Issue -
State: open - Opened by kaiw7 9 months ago
#20 - training logs for AVQA
Issue -
State: open - Opened by kaiw7 9 months ago
#19 - About script of using VPT for AVE
Issue -
State: open - Opened by kaiw7 11 months ago
#18 - dataset shape not match in AVS
Issue -
State: open - Opened by zsevenj about 1 year ago
- 5 comments
#17 - Can't get the accuracy of AVE reported in the paper with vit_base(75.3%)
Issue -
State: open - Opened by Lecooo about 1 year ago
- 2 comments
#16 - Questions about CrossAttention
Issue -
State: open - Opened by kaiw7 about 1 year ago
#15 - some question about VisualAdapter in AVS
Issue -
State: closed - Opened by Divine0719 about 1 year ago
- 2 comments
#14 - Can't get th similar accuracy of AVE reported in the paper (81.1%)
Issue -
State: closed - Opened by liushenme over 1 year ago
- 7 comments
#13 - avsbench shape not match
Issue -
State: open - Opened by Everglow-ZJU over 1 year ago
- 1 comment
#12 - AVQA dimensional error
Issue -
State: closed - Opened by liey1 over 1 year ago
- 1 comment
#11 - Maybe the effect of adapter is not such crucial?
Issue -
State: closed - Opened by Rainlt over 1 year ago
- 2 comments
#10 - Have you noticed that the AVQA model is very unstable when adjusting the lr and batch size?
Issue -
State: closed - Opened by Rainlt over 1 year ago
- 1 comment
#9 - Can't get claimed accuracy (81.1%) with the provided configs?
Issue -
State: closed - Opened by abdurad over 1 year ago
- 4 comments
#8 - How many gpu days does the training procedure of AVQA take?
Issue -
State: closed - Opened by Rainlt over 1 year ago
- 4 comments
#7 - Is this the true config?
Issue -
State: closed - Opened by Rainlt over 1 year ago
- 1 comment
#6 - The address of your paper is wrong?
Issue -
State: closed - Opened by Rainlt over 1 year ago
- 1 comment
#5 - cannot get the claimed mIOU in audio-visual segmentation.
Issue -
State: closed - Opened by junwenxiong over 1 year ago
- 4 comments
#4 - Some bugs are hidden in the AVS repo
Issue -
State: closed - Opened by junwenxiong over 1 year ago
- 1 comment
#3 - For audio, you use both .wav format and .npy. Here is a dimensional error in the code.
Issue -
State: closed - Opened by Bravo5542 over 1 year ago
- 3 comments
#2 - cannot get the claimed accuracy in audio-visual event localization.
Issue -
State: closed - Opened by junwenxiong over 1 year ago
- 2 comments
#1 - erro for AVQA
Issue -
State: closed - Opened by Bravo5542 over 1 year ago
- 1 comment