Comments (1)
Thanks for your interest in our work.
I am wondering if the weight of models (net, head, ssh) still sync ...
I believe so. If they are not synced, the test error of the model will be way worse.
load_state_dict is kind of deepcopy ...
The reason for the deepcopy
is that the key name of the pre-trained checkpoint is slightly different from the model in this repo. Renaming keys in state_dict should not affect parameter values, e.g., https://gist.github.com/the-bass/0bf8aaa302f9ba0d26798b11e4dd73e3.
from ttt-plus-plus.
Related Issues (8)
- Can you release the training code? HOT 2
- Multi-epoch training was performed on the test set. HOT 1
- Pretraining code HOT 1
- Can you release the pre-train model of VisDA-C and corresponding test-time training code? HOT 1
- Clarification on how test time accuracy is calculated HOT 2
- covariance function in cifar/discrepancy.py seems strange HOT 2
- The code in the tent part is incorrect. The affine parameters of the bn layer cannot be updated in model. eval() mode. 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 ttt-plus-plus.