Comments (4)
Hi,
I think first you can load the weights into the supernet, and then inherit the weights from the supernet for each sampled architecture. Specifically, your can obtain the weights from the supernet for each selected operation per layer according to the predifined operation name.
Hope my answer will help you.
from single-path-one-shot-nas.
Thank you for your quick response.
I am actually a bit confused as to how I can implement the approach you mentioned above. Let me try to break it down as per my understanding:
- First I will load the pre-trained weights of the supernet.
- Once the weights for the supernet are loaded, I can generate a list (choice) that will select the random architecture
Now my questions are:
- How do I do this: "Specifically, you can obtain the weights from the supernet for each selected operation per layer according to the predefined operation name."
- Is it possible for me to save the random-selected model just like we can save any other model in PyTorch?
I appreciate your help!
from single-path-one-shot-nas.
As for your two questions:
- The supernet weights is a dict. Each selected operation per layer can be seen as a 'key' for this dict, so you can obtain its corresponding weights from this dict as long as you have the right operation name i.e. the 'key'. The operation name is usually pre-defined when you initialize the model.
- It's not that convenient. You should first initialize a random-selected model, and then inherit weights for each operation in the random-selected model as above, and finally you can save this model with its weights as any other model in PyTorch.
If you have any questions, please feel free to ask.
from single-path-one-shot-nas.
As there are no update recently, I will close this issue.
Feel free to re-open it if you have any question.
from single-path-one-shot-nas.
Related Issues (15)
- Why do i maintain a 10% accuracy rate when training this model? HOT 4
- 请问最终的最高精度能达到多少? HOT 1
- 采样出一条路径后,需要对其他的路径冻结梯度更新吗? HOT 2
- 根据经验,cifar10和imagenet对应的哪些超参需要调整? HOT 1
- 运行完 supernet.py 后,如何进行模型加载校验(val)? HOT 4
- BN校准 HOT 2
- How to do channel search? HOT 1
- 请问下,在block selection时,不同的branch之间会共享权重么? HOT 1
- model test HOT 1
- net output dimension mismatch on cifar10 HOT 7
- about extracting final result HOT 2
- 您好,关于精度复现 HOT 3
- Can not find cifar_train.py HOT 2
- Why shuffle_channels function is not used? 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 single-path-one-shot-nas.