Comments (3)
Oh yes, that was so silly of me! I had been suspecting that I didn't have enough frames in my videos (which I wrote on the other thread as well). Thank you for the quick reply and resolution. Marking the issue closed.
from stylegan-v.
Hi! This is not expected and is very strange. Could you tell how does your dataset structure look like? Are you running from a zip archive or a directory? And could you tell which git hash are you currently using (today, I've updated it to e2f9580)
from stylegan-v.
Ah, ok, I think that I understand the issue. It looks like all your videos are too short (less than 128 frames) and that's why the dataset class discards them when computing fvd2048_128f
, which is FVD computed on top 128-frames-long videos. What you should is not using fvd2048_128f
and fvd2048_128f_subsample8f
metrics. You can do this by removing them from the list here.
from stylegan-v.
Related Issues (20)
- Low IS on UCF101 HOT 16
- Face Forensics dataset preprocessing HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: 'src\\experiment_config.yaml'
- Run stylegan-v Conditionally
- Question about FVD calculation HOT 2
- Question about the release of Pre-trained checkpoints HOT 2
- I tried to generate fake video samples with your pretrained weights but....
- ImportError: cannot import name 'CoordFuser' from 'src.training.layers' HOT 4
- TypeError: Descriptors cannot be created directly
- Projection of real video with multiple frames
- RainbowJelly dataset
- Problem regarding true data statics computation for FVD HOT 4
- Rainbow jelly isn't available
- MOCOGAN: training isn't runing
- Error: batch_size should be a positive integer value, but got batch_size=0 HOT 1
- FVD Metrics HOT 1
- FaceForensics download
- The frame sequence is out of order when evaluating fvd
- I'd like to know how the number 2048 in fvd2048_16f is determined?
- Could you please add an Apache 2.0 license to your project to facilitate downstream repositories using your code?
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 stylegan-v.