Comments (3)
Hi @Sharpiless we were a bit occupied and just looped back to the issues. The generation of ADI samples are an iterative process, i.e., new samples are generated during distillation, when student gradually picks up the knowledge, on top of existing DI images as a starting point. The student network is constantly evolving, and as it picks up knowledge, we iteratively at certain steps, freeze the student, generate ADI images, mixing it into DI pool, and the unfreeze student and continue the distillation. The gradually expands the dataset coverage and facilitate more distillation.
from deepinversion.
This approach leads to a huge computational cost. Because:
- For cifar every time a batch (256 in total) of data is generated, noise data is optimized for 2000 iterations.
- For imagenet every time a batch (1216 in total) of data is generated, noise data is optimized for 20k iterations over 2h.
The above data comes from the paper. And I now have doubts about whether the paper can be reproduced.
As mentioned in issue:#10
from deepinversion.
Complete code may be the best way to answer our questions. I wonder if anyone continues to maintain the repo. Or if there is a follow-up open source plan.
from deepinversion.
Related Issues (20)
- Why the student model is *pretrained* for ImageNet for ADI? HOT 3
- Reproducing Imagenet Knowledge Transfer Top-1 Accuracy HOT 3
- Dataset used in Data-free Knowledge Transfer HOT 1
- VGG Architectures HOT 1
- How to search for hypers on a new dataset HOT 1
- loss about segmentation task HOT 3
- Calculate batch norm statistic loss on parallel training HOT 3
- This error occur unfortunately when I run this project HOT 1
- Are there any plans for sharing KD protocoll? HOT 2
- Question about R_compete term
- How to use the code for ADI? HOT 1
- AttributeError: module 'torch.cuda.amp' has no attribute 'initialize' HOT 2
- Code for Other Experiments HOT 5
- best_cost update HOT 1
- feature_statistics not used HOT 1
- Questions on the KD process on CIFAR10 dataset HOT 2
- Having trouble installing apex and getting the result for the basic snippet HOT 3
- The style of the generated images HOT 1
- What is the KD temperature in the CIFAR10 experiment 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 deepinversion.