Skip to content

issues Search Results · repo:mbzuai-oryx/VideoGPT-plus language:Python

Filter by

27 results
 (91 ms)

27 results

inmbzuai-oryx/VideoGPT-plus (press backspace or delete to remove)

mbzuai-oryx/VideoGPT-plus
Questions about the inference results.

Hello, I would like to ask why the output results after my reasoning are all nonsensical characters like the following. What is the reason for this, and how can I solve it? Are there any friends who have ...
  • shirong52
  • Opened 
    on Feb 28
  • #29

mbzuai-oryx/VideoGPT-plus
About the result of vcg-dev

Hello, thanks for your best work ! When I run bash eval/vcgbench_diverse/inference/run_ddp_inference.sh MBZUAI/VideoGPT-plus_Phi3-mini-4k/vcgbench microsoft/Phi-3-mini-4k-instruct MBZUAI/VCGBench-Diverse ...
  • jun0wanan
  • 2
  • Opened 
    on Oct 25, 2024
  • #28

mbzuai-oryx/VideoGPT-plus
[Question] About pretrain stage batch_size

Hello and thank you for open sourcing this exciting work. May I ask how much the batchsize is set for each of the two projectors during pretrain and are they consistent with llava (16*32)? When reproducing, ...
  • NIneeeeeem
  • 1
  • Opened 
    on Oct 22, 2024
  • #27

mbzuai-oryx/VideoGPT-plus
Question about training data

Hi, thanks for your awesome work! I want to know why training two models for 2（VGG and MV）benchmarks? Why not use all the data to train a single model. Looking forward to your reply! image
  • vvirgooo2
  • 2
  • Opened 
    on Oct 10, 2024
  • #26

mbzuai-oryx/VideoGPT-plus
Question about Dataset

I have a question about the construction of the dataset. Does the keyframe extraction in the paper take only one frame per scene after it passes scene detection?
  • King-king424
  • Opened 
    on Aug 28, 2024
  • #25

mbzuai-oryx/VideoGPT-plus
Issue of garbled text

Thanks for your exciting work! I try to use eval/vcgbench/inference/run_ddp_inference.sh to reproduce the performance on VCGBench with 4*A100 GPUs, but the generated texts are garbled as follows: [ { ...
  • ShuyUSTC
  • 2
  • Opened 
    on Aug 13, 2024
  • #24

mbzuai-oryx/VideoGPT-plus
Zero-shot QA evaluation

How to perform zero-shot QA evaluation on datasets like MSVD-QA, MSRVTT-QA, TGIF-QA, ActivityNet-QA? Could we just follow the pipeline of Video-ChatGPT？
  • hulianyuyy
  • Opened 
    on Aug 8, 2024
  • #23

mbzuai-oryx/VideoGPT-plus
Inquiry about Costs Associated with Video LLM Benchmarks

Hello everyone, I have been working on replicating benchmarks related to video-class Large Language Models (LLMs), and I ve noticed that most of these benchmarks rely on the GPT-assistant framework. Given ...
  • hb-jw
  • Opened 
    on Jul 26, 2024
  • #22

mbzuai-oryx/VideoGPT-plus
Support for Multi-turn Conversations with Fixed Video Input?

Hello, I have a question regarding the conversation capabilities of this project: 1. Does the system support multi-turn conversations? 2. Is it possible to have a natural, ongoing dialogue while keeping ...
  • YoungjaeDev
  • Opened 
    on Jul 23, 2024
  • #21

mbzuai-oryx/VideoGPT-plus
Where can I find the dense captions for the 112K videos?

Thank you so much for sharing this amazing work! I’m wondering where I can find the dense captions for the 112k videos mentioned in the paper.
  • ronghangzhu
  • Opened 
    on Jul 22, 2024
  • #20
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub