Comments (2)
Yes, you're correct. The once-for-all network training will take no more than 2 days on a single 1080Ti.
from gan-compression.
I have read the Appendix 6.1 on the paper, and the authors have provided the complete pipeline of the training.
- train a MobileNet style network from scratch (teacher network)
- distill a smaller student network using the network train in the previous stage
- initialized by the student network, train ta "once-for-all" network
- evaluate all sub-network under a certain computation budget
- choose the best-performing sub-network within the previous step and fine-tune the compressed model for the final model.
For the second stage, I am guessing the author has transferred the weight of the teacher to the student network using load_networks
.
Finally, the authors provided Table 5. for training details such as training epochs (for training from scratch, distillation and fine-tuning) and once-for-all network training. For pix2pix and cycle gan they have doubled the epoch for once-for-all network compared to the training/distillation/fine-tuning.
I guess this answers all the questions I had.
Please correct me if I got something wrong.
from gan-compression.
Related Issues (20)
- Gray-Scale Input Support HOT 1
- What do these two paths mean?(--metaA_path --metaB_path) HOT 3
- About Select the Best Model (evolution_search.py) HOT 2
- distilling on higer resolution HOT 2
- Distill Problem HOT 4
- "Once-for-all" Network Training Problem HOT 2
- TypeError: _output_padding() missing 1 required positional argument: 'num_spatial_dims' HOT 4
- Guidance to covert pth to ptl
- [Question] About SuperSeparableConv2d HOT 2
- Cannot access to https://hanlab.mit.edu/ HOT 1
- ERROR 403: Forbidden HOT 5
- Request for Access to Pretrained Model for Verification and Replication Purposes. HOT 3
- URL is not supported HOT 7
- Does this way can apply to pix2pixHD model? HOT 2
- How to generate cityscape_A.npz HOT 1
- where is bash scripts/cycle_gan/horse2zebra/search.sh? HOT 1
- "download_real_stat.sh" doesn't work.
- Question about testing the compressed model HOT 1
- Question about the budget setting HOT 2
- about SuperConv2d 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 gan-compression.