Comments (4)
Thanks for reporting. I remembered testing it before releasing this code repo and got FID 2.20. Could you try the non-deep version and see if you can obtain an FID similar to the one reported in paper? The seed in config files is probably not used anywhere—it's from the JAX repo.
from score_sde_pytorch.
I'm currently running other experiments and will try the non-deep version in 1~2 weeks. Also, I ran sampling with the checkpoint provided in this repo and it has FID 2.20, so I'm thinking the seed might caused the difference in training process.
from score_sde_pytorch.
Hi @yang-song,
I've tried the non-deep version (configs/ve/cifar10_ncsnpp_continuous.py) and the result is
I0620 20:25:37.822132 140001873700672 run_lib.py:402] ckpt-24 --- inception_score: 9.829116e+00, FID: 2.684183e+00, KID: 6.818869e-04
I trained for the same amount of steps and used the same batch size, but its a bit worse than the result from the paper.
from score_sde_pytorch.
Thanks for reporting. I will need some time to run those programs and compare the implementation with our internal code at Google. In the meanwhile, one potential reason is different random seeds causing the optimal checkpoint number (the one that minimizes the FID score) to be different.
from score_sde_pytorch.
Related Issues (20)
- Question about Eq. (4) and VP SDE implementation HOT 1
- KeyError: 'ncsnpp' of get_models() in models.utils HOT 3
- CUDA_HOME environment variable is not set. Please set it to your CUDA install root HOT 2
- Issues on evaluation
- ConditionalResidualBlock not working
- Question about the scaling operation of score function of VP and VE HOT 1
- PC sampler mismatched? HOT 3
- Question about reporting likelihoods in bits per dim HOT 4
- ImportError: cannot import name 'ParamSpec' from 'typing_extensions' HOT 1
- an error of the upfirn2d.py HOT 2
- Question about conditional generation
- How to calculate the score of a new unseen datapoint by a score based diffusion model?
- Some tips on why the model ain't working HOT 1
- The name tf.estimator.tpu.TPUEstimator is deprecated. Please use tf.compat.v1.estimator.tpu.TPUEstimator instead. HOT 1
- Segmentation fault (core dumped) HOT 1
- Likelihood estimation
- why pytorch version uses tensorflow? HOT 1
- Problems installing dependencies and getting code to run
- ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group
- Wrong Likelihood Computation for VE SDE 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 score_sde_pytorch.