Comments (10)
By default -m
is not specified. In that way, the algorithm will go through the whole dataset. The step-wise, detailed guidance is written in README.md -- please be specific about the part which you don't understand. Meanwhile, this code base is connected with two papers, please be specific about the name of the paper.
from robrank.
In the paper you can find that the algorithm will go through the whole dataset for reporting the number. -m
is mostly used for debugging, and can be directly omitted.
from robrank.
ok,thanks a lot. I want to reproduce the result of 《Enhancing Adversarial Robustness for Deep Metric Learning》. However, it is relatively different from the results of the paper. Is it normal?
from robrank.
I follow the step of README.md, I think there's no wrong step. And the result is trained on CUB dataset
from robrank.
This difference is normal. What you see here is within the error bar. Due to different initialization and other factors (such as the number of GPUs in DDP mode), the performance differs slightly. If you want to see a higher ERS, just try to limit the GPU number to 1 or 2 (if I remember correctly. If not, it should be the reverse way -- more GPUs -- there will be a slight trade-off between R1 and ERS when changing the GPU number. This is a common phenomenon in parallel training), and try some more initialization.
from robrank.
ok ,I will try it. As to the R1/R2/mAP/NMI in your paper, are they the result of training end?
from robrank.
Yes, they are reported at the training end status. Because in adversarial training, these standard benign metrics may look like a U-shape curve or directly a descending curve ... That's a part of adversarial training sacrificing the benign performance.
from robrank.
Get it, thank you very much!
from robrank.
Excuse me, which is the mAP in 《Enhancing Adversarial Robustness for Deep Metric Learning》, mAP or mAP@R?
from robrank.
It's simply the original mAP. If mAP@R is used, it should have been explicitly justified.
from robrank.
Related Issues (18)
- [doc] enrich documentation strings for robrank.cmdline
- usage of the script tools/pjswipe.py
- [dev] put old model configs into autogen.py as well.
- Name 'os' is not defined. HOT 2
- How to Conduct adversarial attack against deep classifier HOT 1
- Code for "Enhancing Adversarial Robustness for Deep Metric Learning" HOT 3
- migrate to pytorch-lightning 1.6.X
- provide pretrained checkpoints HOT 1
- Validating saving checkpoints (peculiar issue with reloading) HOT 7
- [classification] merge neuroski codebase from my private repository.
- [doc] how to prepare data?
- compute mAP@R HOT 1
- Training deep metric learning model HOT 2
- [model] add wide resnet family HOT 1
- [act] reduce memory footprint HOT 5
- [config] margin for sampling HOT 1
- model.config.maxepoch HOT 3
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 robrank.