Comments (4)
Hi @doantientai, the FID value is a sort of difference between two Gaussians and comes from Frechet Distance computation. The reason for NaN FID value could be small number of samples (<2048). You can see two different frechet distance computation methods in inception_utils.py . As default it uses the 'torch' method. So try the 'numpy' method instead of 'torch'. I hope it works.
from biggan-pytorch.
Thank you @damlasena, I switched to numpy method and it works. I also think that the line 306 in inception_utils.py should be:
FID = numpy_calculate_frechet_distance(mu, sigma, data_mu, data_sigma)
instead of:
FID = numpy_calculate_frechet_distance(mu.cpu().numpy(), sigma.cpu().numpy(), data_mu, data_sigma)
because in the line 299, mu and sigma are already converted to numpy arrays
from biggan-pytorch.
Hi, @doantientai @damlasena. Is there anyone who finds that numpy_calculate_frechet_distance will cost a lot of time? For example, when I want to vilify the model performance, it cost me almost 1 day or more to calculate the metric. I don't know why I cost so much time! So, someone who can help me fix this problem? Thanks!
from biggan-pytorch.
BTW, I use the V100 32GB device with 8 CPUs
from biggan-pytorch.
Related Issues (20)
- Training with 96x96 input HOT 1
- 我长期研究和改进GAN,如果对GAN或者深度学习感兴趣的可以联系我,联系方式,wechat: lovedaixiaobaby
- How can I improve the quality of generated images?
- AttributeError: 'Distribution' object has no attribute 'dist_type' HOT 2
- why the inception scores and FIDs are not comparable with the TF version?
- Out of memory HOT 3
- requirements.txt or library versions
- Training with ImageNet 64x64 HOT 1
- sampling out of memory HOT 1
- Correct attention layer implementation HOT 4
- y_ and y variables in training function
- Query about orthogonal regularization implementation
- collapsed samples
- Trouble training it from scratch
- BigGAN-deep pre-trained
- How to train BigGAN for image generation conditioned on text description? HOT 1
- set cross_replica as true got bad result HOT 1
- Output 80x688 images
- Problems when sampling
- The model was trained. How to generate the images?
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 biggan-pytorch.