Comments (12)
Most of the videos are common and relatively easy to obtain. For some datasets that are more difficult to access, for EgoQA videos, download them from this link. For VideoChat2 conversation videos, download them from link. For Youcook, you can download it from link
from ask-anything.
@yinanhe Thanks very much 🍻
from ask-anything.
Hello, @yinanhe, how to download the CLEVRER dataset? The link shows noting.
from ask-anything.
@pengzhiliang
You can download from the link below.
Training Videos, Annotations, Questions and Answers
Validation Videos, Annotations, Questions and Answers
Testing Videos, Questions
Object Masks and Attributes
Readme
from ask-anything.
@yinanhe Do you have alternative links? The videos links aren't working for me.
from ask-anything.
@schopra8 We no longer have any other links. If you are still having difficulties in getting the data, please let me know which dataset it is.
from ask-anything.
Apologies for the lack of specificity! I mean the CLEVRER dataset specifically. The question+answers and README load for me -- but the videos don't, when I click on those links.
I reached out to the original authors of the CLEVRER dataset as well, but they haven't responded.
from ask-anything.
@yinanhe -- I'm also struggling to find the VideoChat videos used in the conversation and caption annotations. Do you have any pointers to where I can download this data? Thank you in advance!
from ask-anything.
Apologies for the lack of specificity! I mean the CLEVRER dataset specifically. The question+answers and README load for me -- but the videos don't, when I click on those links.
I reached out to the original authors of the CLEVRER dataset as well, but they haven't responded.
@schopra8 how about use link in #176 (comment). In my network environment, the download is normal.
from ask-anything.
@yinanhe -- I'm also struggling to find the VideoChat videos used in the conversation and caption annotations. Do you have any pointers to where I can download this data? Thank you in advance!
The videos used here are from YouTube, and some videos might be found in the InternVid dataset on opendatlab.com.
from ask-anything.
Thank you @yinanhe!
-
For CLEVRER it looks like my browser was automatically trying to turn the HTTP link into HTTPS and that was why the file was not downloading. This works for me now.
-
For the VideoChat portion of the VidChat2 Instruction Tuning data I see file names like "000551_000600/1054295129.mp4" but when I look at the InternVid-10M dataset in HuggingFace I only see YouTube Ids (e.g. "HdYoyzCSWyw"). How does one align the YouTube IDs to the names in the VidChat2 Instruction Tuning dataset?
from ask-anything.
I now see that the VideoChat data names correspond to WebVid like VideoChat2 -- and can resolve the videos.
@yinanhe - Thanks for all the help! It might be helpful to update the Data.md
file to clarify that VideoChat corresponds to videos from WebVid. The link to InternVid
threw me off -- and had me incorrectly looking at the InternVid-10M Dataset .
from ask-anything.
Related Issues (20)
- mistral版本三阶段训练代码问题 HOT 5
- 请问后续是否会支持lama3的LLM HOT 2
- New datasets used for videochat2_mistral HOT 4
- I'm kinda curious,When load the mistral_model,why I get this warning? HOT 1
- Attention mask and pad token id warning in videochat2_mistral HOT 1
- Mistral Prompt Template Deviation (Instructions / System Prompts) HOT 2
- Instructions vs. Questions in Instruction Fine-Tuning Dataset HOT 2
- MVBench Leaderboard broken HOT 1
- how to implement batch_chat for videochat2 benchmark? HOT 1
- More large LLM potentials needed for the community! HOT 1
- can I simply set vit_l14 to larger input image size, such as 336/448, without re-training for stage2/3, videochat2? HOT 2
- nan loss for stage3 training of videochat2_mistral HOT 14
- Bug Report: Identical Start and End Timestamps in object_interaction.json of MVBench HOT 2
- More GPU memory for new mistrail version.. HOT 4
- Questions about VideoChat2_HD HOT 20
- The evaluation for EgoSchema HOT 7
- question about vision encoder HOT 1
- Suggestion about MVBench HOT 2
- No star/Charades_v1_480/EDXBD.mp4 in the new MVBench (AS) HOT 1
- Discrepancy in Image ID Alignment Between M3IT and VideoChat2IT
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ask-anything.