Comments (6)
Hi,
Unfortunately, the training under the pytorch framework is non-deterministic. A relevant issue is here: https://discuss.pytorch.org/t/random-seed-initialization/7854/18 Even though we re-run the code, there still exists some fluctuation, but it is not difficult to get a value higher than 44% (with batch size = 2).
To your guess,
- During the final testing, we use 1024x2048. As you tested, we think it doesn't affect too much.
- Our apologies. That's a typo. Following the setting of Tsai et al., we use exactly the same initial weights as Deeplabv2 used, so the code is correct. A relevant issue is here: wasidennis/AdaptSegNet#5
The potential reason could be the version of libraries. I am re-running my code with batch size = 1. I hope I can come up with some good results and random seed to help you reproduce the performance.
--- edit ---
In total, the model will be trained for 250000 steps. The smaller batch size you use, the less samples the model sees (i.e. you only see half of the number of data as compared to mine). It could be helpful to train for more steps and adjust the learning rate moderately.
Cheers,
Hui-Po
from dise-domain-invariant-structure-extraction.
Thank you for all the suggestions. I will try them out and see if I can improve the values.Please let me know if you are able to get to the value of 44% with batch size = 1.
from dise-domain-invariant-structure-extraction.
hello,i run the code,but my device is two 1080GPU,i want to know that what are your device? and how long you cost to train the model? @subeeshvasu
from dise-domain-invariant-structure-extraction.
@crazygirl1992 I was using a single GTX TitanX (12 GB). With this settings, for batch size = 1, training cost was approximately: 2hrs, 20 minutes per 1000 iterations.
from dise-domain-invariant-structure-extraction.
thank you very much,and can you achive the paper's result now? the training almost 250000 iterations in his paper,and 20*250mins,not 2hrs
from dise-domain-invariant-structure-extraction.
I couldn't get those values. With batch size = 4, one could reproduce the values I guess!.
from dise-domain-invariant-structure-extraction.
Related Issues (12)
- FCN8 code HOT 4
- what about multi-gpu training? is it possible?
- The source only results of Cityscapes
- The pretrained weights cannot be downloaded HOT 3
- Domain classifiers HOT 2
- Possible to run it on a 12 GB GPU ? HOT 1
- deeplab optim_parameters not called. same lr rate for all layers HOT 2
- About Source-Only Performance HOT 3
- 11GB GPU for training HOT 3
- Translation Texture Loss is missing HOT 2
- pytorch version and results reproduction HOT 3
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 dise-domain-invariant-structure-extraction.