Comments (3)
@tingxueronghua Were you able to resolve the problem? I am able to start finetuning on my local gpu but on any other machine I get the same CUDA out of memory error which is not the correct behavior.
from albef.
maybe you made the same mistake with me? In distributeddataparallel, the batchsize means that per GPU. So when i set batchsize to 4, it means 16 totally. and i can run the code when i set batchsize to 2.
from albef.
Thanks for your quick reply!
I am running it with batchsize 1 yet getting this error even with single gpu. :/
from albef.
Related Issues (20)
- change english text_encoder to other language? HOT 2
- Question about answer ranking HOT 2
- Zero-shot capabilities on ImageNet HOT 2
- state_dict = checkpoint['model'] KeyError: 'model' When I using flickr30k.pth HOT 2
- Grounding det.json file for other grounding datasets
- pretrain task
- utils.init_distributed_mode(args) Fail HOT 1
- About dropout and no_grad.
- refcoco on lower resolution
- ITM loss HOT 1
- RefCOCO+ Fine-tuning
- TypeError: '<=' not supported between instances of 'float' and 'str' ? HOT 1
- How can I get Visual Genome ? HOT 2
- ITC & ITM & MLM weight distribution
- RuntimeError: invalid multinomial distribution (sum of probabilities <= 0)
- '/export/share HOT 2
- The code for loss computation of itc is not corresponding to the original paper HOT 2
- Overflow in `autocontrast_func`
- Reproducing the VQA candidate answers from the dataset and paper
- About the Flickr-30k dataset HOT 1
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 albef.