Comments (2)
Hi @txz741,
thanks! In your case it's using the resnet50 from timm and not the checkpoint from torchvision. Are you using the provided environment? It seems like you're using, e.g., the wrong PyTorch Version (1.10.0 instead of 1.13.1). Make sure you have torchvision 0.14.1 installed as well.
Regarding the CIFAR-C results: I'm not sure, if I understood it correctly. Are they consistent with the paper or inconsistent? Thanks!
All the best,
Mario
from test-time-adaptation.
Wonderful! Now the results of ROID on imagenet-c can be reproduced perfectly! I may never address the issue without your help since I may never suspect the environments and pretrained models.
Regarding the CIFAR-C results, they are consistent with the paper (sorry for my expression before), because the pretrained models of CIFAR-C are adopted from the official google drive links of RobustBench, no confusion about choosing timm or torchvision.
Thanks again for your timely and accurate response!
Best regards,
txz741
from test-time-adaptation.
Related Issues (12)
- Which part of parameters are updated? HOT 1
- The settings of continual test-time domain adaptation HOT 2
- a basic question about TTA HOT 1
- Unable to run ViT experiments HOT 4
- wideresnet object has no attribute 'model' HOT 2
- The segmentation task HOT 1
- Cannot reproduce the results on "correlated" setting for CIFAR-10C HOT 1
- Can you provide the code of rmt method for semantic segmentation? HOT 1
- Cannot run the RMT method without exemplars HOT 1
- mixed domains TTA setting HOT 2
- Adding new method SANTA HOT 1
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 test-time-adaptation.