Comments (3)
Good question! Can you try to use a small batch? From my previous experience, the results are similar.
Besides, if you want to use gradient accumulation, I think the multiple modalities in an iterator
will be a good baseline, but some papers argue that single modalities in an iterator
will be better. If you want to realize it, a simple strategy is to split the input data manually.
from ask-anything.
There is an ablation in our paper. And 0 extra query lead to poorer performance on MVBench
from ask-anything.
Thank you for your response. I have another question regarding the extra_num_query_tokens. Specifically, I'm interested in understanding if you've tested the scenario where this parameter is set to 0. How does this compression of visual tokens affect performance?
from ask-anything.
Related Issues (20)
- No module named 'models.videochat2_it' HOT 6
- source video links not available HOT 5
- difficulty running mvbench.ipynb HOT 4
- no module name datasets HOT 11
- Why is the output garbled HOT 1
- Issue with MVBench Evaluation
- What does this code mean HOT 1
- Release of GPT scripts to generate the QA data for MVBench HOT 1
- 怎么进去微信或者Q交流群? HOT 1
- running video_chat2 HOT 2
- checkpoints of UMT HOT 1
- download links for the datasets HOT 3
- 请大佬教一下怎么在自己的电脑上训练 HOT 32
- UserWarning: None of the inputs have requires_grad=True. Gradients will be None HOT 8
- Missing video data in MVBench CLEVRER validation set HOT 1
- videochat2可以同时输入多个视频然后进行处理,以供下游任务吗? HOT 1
- Best option:( doesn't work HOT 1
- text_input的形式
- functions for MVBench eval in demo_mistral.ipynb
- RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method
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.