Comments (1)
To train on 2 GPUs, you have to set --num-gpus 2
in your training command. If your GPUs have enough memory, you should be fine without changing any config parameter. If you run out of memory, you can try one of the following:
- reduce the batch size until it fits your memory, e.g. start your train command with
SOLVER.IMS_PER_BATCH 10
or an even lower value. - reduce the crop size: Change the INPUT.CROP.SIZE parameter in
MGNet-Cityscapes-Fine.yaml
to a lower value, e.g.(960, 960)
. Change OHEM_N_MIN accordingly.
However, keep in mind, that both methods will likely decrease performance of the final model.
Based on our experiments, you do not have to to change OHEM_N_MIN, if you train on less than 4 GPUs, just if you change the crop size. I will update the misleading comment.
from mgnet.
Related Issues (3)
- inplace-abn HOT 3
- about the datasets and reproduce HOT 6
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 mgnet.