Comments (2)
Hi,
I believe there are two problems here.
First, regarding the wrong checkpoint, sorry for this inconvenience. I have previously updated the correct version of the checkpoint on SVHN. You could download it from the link in README. What I want to stress here is that the mistake ONLY happens during the conversion from our private-trained models to pytorch-available models for the aim of publishing the code, more details described in #5 (comment), nothing wrong involved in the training or testing process using our private distributed framework. Therefore, the way you truncate the first 10 dimensions of the checkpoint actually gets the correct parameters.
Furthermore, regarding the results, the difference from the paper is because, when I was implementing the training code for this repo, I found the cosine-decay learning rate can help a lot to increase the final adversarial performance (where the numbers reported in the paper are using the step-decay learning rate scheme). I have tested it on CIFAR and SVHN. On CIFAR it works nice and I have updated it in the code, but for SVHN, it is hard to train. Additional tricks are required, i.e. you need to first train the model on clean data for several epochs then finetune it with the adversarial attack, and use a large batch size. And it helps the RobNet_free to work, yet unfortunately not for the RobNet_large. So the checkpoint of RobNet_free is trained using cosine-decay learning rate, and as you can see, it yields far much better results than those of the step-decay learning rate. We did not include this in the paper, since if we do, it is unfair for the comparison of other models. But for this public use, I believe the better performance will be more helpful.
(To help understand what I am saying, you can evaluate the result of RobNet_large using the same way you treat it with RobNet_free to get the correct performance and compare it with the paper. Sorry again for so much inconvenience introduced by the previous stupid mistake...)
from robnets.
Thanks.
from robnets.
Related Issues (19)
- Could you open source the whole training code? HOT 2
- Can this code be used to reproduce the MobileNetV2 numbers in the paper? HOT 1
- How to do one-shot nas?
- How to do archchtecture search on supernet? HOT 4
- How to train supernet? HOT 1
- why not use the torchvision dataset for SVHN? HOT 1
- How to extract top architecture from supernet?Is it achievable?
- Obtain the different architectures mentioned in the paper
- Information on Sampled Networks?
- The natural accuracies of ResNet18 and ResNet50 in CIFAR10
- The natural accuracies of ResNet18 and ResNet50 in CIFAR10
- about the checkpionts ?
- How to calculate the number of MAC, the number of layers and the model size of the network? HOT 1
- Have the ckpts been fine-tuned w.r.t. the hard-coded architecture? HOT 5
- SVHN HOT 2
- Where can I find the checkpoint file to use searched RobNet models? HOT 2
- How big is the difference in training time and memory consumption between using and not using adversarial training in the search network process? HOT 3
- Tiny ImageNet Training Configuration HOT 4
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 robnets.