Comments (2)
Another Question, when I try to use multi-process-evaluation, no matter I input device=[3,5,6,7] or [0,1,2,3] when CUDA_VISIBLE_DEVICES=3,5,6,7. The occupied GPU is always only 0. How should I solve it?
from fasterseg.
Hi @NoOneUST!
Thank you for your interest in our work!
The differentiable NAS formulate the search space as the model (e.g. convolution weights) and architecture (determines which operator to use in each cell). During the search, the model parameters and the architecture parameters are alternatively optimized. Thus, we need both of them.
To enable the multi-gpu training, you have to at least wrap the nn.Module
into nn.DataParallel
(which I did not implement here).
from fasterseg.
Related Issues (20)
- How can FasterSeg be used to perform inference on a video? HOT 6
- I reported an error on my own data set while I was infering HOT 3
- Test Issue HOT 1
- Training with custom data with different resolution to cityscapes dataset HOT 1
- TranA and TrainB is overlapped according to your implementation HOT 5
- NaN values in loss function during Step 2.2 HOT 2
- BaseDataset.__getitem__ always returns random item if file_length is set HOT 1
- CUDA out of memory: GeForce GTX 1650. HOT 1
- Which Nvidia GPU card do you use for training? HOT 2
- What's the idea of `betas2path ` ? HOT 3
- CUDA out of memory HOT 2
- How to estimate the runtime of the four steps depending on epochs and iterations?
- RuntimeError: transform: failed to synchronize: cudaErrorAssert: device-side assert triggered
- error during run_latency.py HOT 3
- Whether the architectures are different after each searching?
- Custom Data Resolution for Training HOT 10
- RuntimeError:CUDA error:API call is not supported in the installed CUDA driver HOT 1
- Setting up on Windows
- Model mismatch occurs when training student network with own data set HOT 2
- A train_fine_val.txt file
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 fasterseg.