Comments (8)
Hi are you doing the experiment from GTA5->Cityscapes? I guess the problem is from the first stage that you got 41.98, which is a bit low than what is expected. I suggest you to train more iterations in the first stage. In our experiments, we got BEST IOU at around 80k iteration or so. And also double check your learning rate, image size, pytorch version, etc.
from intrada.
I am doing the experiment from GTA5->Cityscapes.
I just use your default settings.
How much miou do you achieve for the first stage?
By the way, pytorch version is 1.5, CUDA10.1
from intrada.
We conduct the experiment on pytorch=0.4.1 and our best miou would be around 43.8 for the inter-da stage. Right now you are using pytoch=1.5. I guess it is probably due to pytorch version but I am not really sure. I will double check it on my local server.
from intrada.
With pytorch0.4.1, i got 42.4miou at 5w iters. I have finished 10w iters.
from intrada.
It's still a bit low than expected. We usually got 43.8± 0.2. Actually our experiments setup of inter-da keep the same as ADVENT.
from intrada.
A little concern is also from the CUDA version. As I tried on my machine, by using CUDA=9.2 I got the same performance, rather it becomes lower when I switch to CUDA=10.2. So be careful about which cuda version is used currently.
from intrada.
With pytorch0.4.1, i got 42.4miou at 5w iters. I have finished 10w iters.
Hi, I was using pytorch1.5.1 and CUDA10.2. I was able to achieve 43.75 for ADVENT, the first stage. And 46.28 for the second stage adaptation.
from intrada.
Hi @xdeng7 thank you for your effort and sharing this information!
Regards
from intrada.
Related Issues (16)
- how to train model on custom dataset HOT 7
- Two-phase Pseudo Label Densification for Self-training based Domain Adaptation HOT 2
- About Pretrained and evaluation models HOT 1
- Could you update the entire training code of intraDA? HOT 1
- Who can share me the pretrained model, the download url was broken.
- Can't get the 47% mIoU
- 目标域没有标签 HOT 7
- No color_masks HOT 1
- is there a batch size of 1 per gpu? HOT 4
- pretrained model for resnet50 backbone HOT 3
- IntraDA trained from scratch or from InterDA params? HOT 1
- How to implement from Synscapes/SYNTHIA to Cityscapes? HOT 1
- Entropy Maps HOT 1
- The initial parameters of the model for intra-domain adaptation HOT 1
- About trained model of ADVENT HOT 2
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 intrada.