Comments (2)
lmxyy
commented on July 17, 2024
Sorry, could you please tell me which model are you compressing?
Since search_multi.py sometimes may cause a deadlock, I didn't update it for some time. So I do not recommend you use it.
If you need parallel multi-GPU searching, you could manually split the search space with search.py. All you need to do is add additional arguments --split and --remainder. For example, if you need to search the sub-networks for cycleGAN with 2 GPUs, you could use the following commands:
python search.py --dataroot database/horse2zebra/valA \
--dataset_mode single \
--restore_G_path logs/cycle_gan/horse2zebra/supernet/checkpoints/latest_net_G.pth \
--output_path logs/cycle_gan/horse2zebra/supernet/pkls/result0.pkl \
--ngf 32 --batch_size 32 \
--config_set channels-32 \
--real_stat_path real_stat/horse2zebra_B.npz \
--split 2 --remainder 0And on the second GPU
python search.py --dataroot database/horse2zebra/valA \
--dataset_mode single \
--restore_G_path logs/cycle_gan/horse2zebra/supernet/checkpoints/latest_net_G.pth \
--output_path logs/cycle_gan/horse2zebra/supernet/pkls/result1.pkl \
--ngf 32 --batch_size 32 \
--config_set channels-32 \
--real_stat_path real_stat/horse2zebra_B.npz \
--split 2 --remainder 1 --gpu_ids 1And then you could merge the search results with merge.py:
python merge.py --in_dir logs/cycle_gan/horse2zebra/supernet/pkls --output_path logs/cycle_gan/horse2zebra/supernetI will try to fix the search_multi.py.
from gan-compression.
techmonsterwang
commented on July 17, 2024
Good solving method, I'll try it! Thanks for the answer!
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.