Comments (3)
hi. @xingyueye, this phenomenon has been founded and explained by many papers. To my way of thinking , there are two aspects. First, in the early stage of the training, weights are not well learned and may produce worse features (not consistent) and weights-free operations are easier to bypass gradients. That's why we use a few epochs to warm up the super-net. Second, the if we enlarge the epochs, e.g.(100 or 200), darts may suffer from overfitting problem. Some works try to solve this problem by regularizing or early stopping [1,2,3].
[1] DARTS+: Improved Differentiable Architecture Search with Early Stopping
[2] Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
[3] Understanding and Robustifying Differentiable Architecture Search
from pc-darts.
Thanks a lot, your respond is helpful, And I would study the papers you recommended asap.
My guess is similar to your first opion, So I add warm_up to Darts sa well, but results are terrible. I set up three sets of experiments with warm_up epoch of 20, 30, and 40, but the search results show that skip_connect would appear rapidly and exceed 2 when the warmup period ends and the architecture search begins. I saw that your warm_up epoch nums is 15. So I guess that the warm_up epoch in my exp were setted unsuitable or that it differ between Darts and PC-Darts?
from pc-darts.
@xingyueye , sorry for the late reply as CVPR deadline is approaching. Original DARTS suffer lots of problems besides the mentioned. If warm up epochs are too large, DASRTS still prefer SKIP.
from pc-darts.
Related Issues (20)
- Is a channel sampling mask fixed? HOT 3
- Is there any plan to release the pretrained imagenet model? HOT 1
- Why modifying architecture after epoch 15
- Data preparation of ImageNet
- How to change the channel proportion K? HOT 2
- Cannot re-implement your claimed result HOT 3
- GPU Utilization is Bad HOT 1
- We cannot obtain your claimed result on ImageNet after trying many configurations HOT 4
- Question about search on custom dataset HOT 5
- test.py运行报错
- Understanding the two sets of the architecture hyperparameter HOT 2
- how you report the final accuracy in evaluation? Possibly touch the test set for the best acc? HOT 2
- Learning rate schedule
- 你好,结果不一致 HOT 2
- Searched genotype remain / keep unchanged for a great number of epoch HOT 2
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1!
- 您好,想请问一下网络搜索完之后如何得到需要的网络结构代码? HOT 3
- About the license of this repository
- Hello, whether PC-DARTS likes DARTS with extra dropout?
- Not Enough Comments in the Code
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 pc-darts.