Comments (3)
Hi José,
Yes, this is OOM error. Please change batch_size in wikisql.conf to smaller one. The current 256 setting is trained on my GPU cluster with 4x48GB memory, for 1x32GB I recommend to try batch_size=32 first.
Note that smaller batch size could result in lower accuracy, please refer to my reply here #9
from hydranet-wikisql.
Sorry, one correction:
- If you specify --gpu 0, then it uses Nvidia RTX 2070 (8GB gpu memory?), so batch_size should be ~8.
- If you don't specify --gpu, then it uses ram (32GB), so batch_size should be 32.
If there is still OOM issue, please keep decreasing batch_size until no error
from hydranet-wikisql.
Thank you for your promptness in answering me!
I'm actually not quite sure about all of this, I'm just helping someone run on my computer because they thought it would work out of the box.
I'll try running with a small batch size, and I'd actually like to note that not specifying --gpu was not enough to make it use CPU and RAM, not as far as I noticed it.
from hydranet-wikisql.
Related Issues (16)
- KeyError: 'token_type_ids' HOT 7
- Got different Result HOT 8
- While doing prediction facing this error HOT 15
- Code on chinese dataset TableQA HOT 2
- How to use different model HOT 1
- How to use other pretrain model in this code? HOT 2
- Export to ONNX Model possible?
- How to run model on a single question? HOT 1
- RuntimeError: unexpected EOF, expected 3539973 more bytes. The file might be corrupted. HOT 4
- Can I use the model to test a new question and a new table? HOT 2
- a bug on a sub task val accuracy when training on multi GPUs HOT 4
- Can I predict using the model on windows with cpu only? HOT 6
- Is there any Issue on accuracy score on EG cases ? HOT 2
- Question about Ranking score in your code HOT 1
- Ask about the result HOT 5
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 hydranet-wikisql.