Comments (9)
Hi, thanks for your interest in our work.
In our paper, we use all the training samples and the generated samples in all classes to compute FID (not per-class FID and average the result).
We find most of the previous papers report the FID in this way.
The mean and the standard derivation are calculated based on five independent trials. Please see the appendix in our paper.
from msgan.
Wow super prompt reply! Thanks!
I misunderstood the sentence in the appendix 'We use all the training samples and the generated samples to compute FID.'. Now I see the point. 5K samples per class and 50K in total and all 50K samples are used to compute a single stats.
(What a waste of time writing per-class FID..... stupid me lol)
Further explanation on five trials is also valuable.
Could you explain whether it means
- five different models from five training trials (probably this one is the right one but just for double check..)
- or five testing for one fixed model (randomness from sampling z from Gaussian)
?
from msgan.
We just used one fixed model and generated five times of samples.
Hope it helps.
from msgan.
Thanks!
Finally I got FID of 28.60 from your pretrained model.
However, the model trained by myself reports 35.66.
Did you observe variation among multiple training trials?
I will re-run the training for several times anyway but any comments will be helpful since training for 200K iters takes about 10 hours on my machine.
Is weight_decay on optimizer is accidentally not mentioned in the paper or not erased from your code?
Or, do I have to train for more than 200K iters?
from msgan.
We just obtained the pre-trained model using the codes released and reported the five times of the results using that model.
from msgan.
Thanks it means that I can keep working on the same code!
I will train again several times and share my experience.
Thank you again :)
from msgan.
I ran the same code for four more trials and got FIDs below.
trial0: 29.93222174258068
trial1: 30.902965756971412
trial2: 29.98750439731532
trial3: 35.25630393016536
Probably measure of the provided pre-trained model can be reached in a few more trials.
from msgan.
Hi, I find I set the max_iter=200,000 in my code. In fact, I remembered I trained 200 epochs of the pre-trained model.
from msgan.
Oh, now I see that!
My 00199.pth are not actually from after 200 epoch hahahahaha.
Thanks I will try without if total_it >= max_it:
block :)
from msgan.
Related Issues (20)
- Do you use L1 Loss in pixel2pixel model? HOT 7
- some trouble inDCGAN HOT 2
- 是不是没有上传几个预训练的embedding layer呀? HOT 1
- Numpy as training input HOT 1
- a question about DCGAN HOT 2
- Questions about DRIT HOT 2
- How many images used for computing FID? HOT 1
- where is the appendix of the paper? HOT 1
- Minor mode collapse problems HOT 2
- NBD and JSD HOT 1
- how to train this model on my own database?
- Mode Seeking Loss does not decrease HOT 1
- Reciprocal of mode seeking loss HOT 2
- LPIPS HOT 4
- Learning rate decay for cat2dog dataset HOT 4
- Replicating Pix2Pix experiment on maps dataset
- NDB & JSD Reproduction Problems
- Question about applying mode seeking regularization term to multi-scale structure similarity loss (MS-SSIM)
- What is the difference between DSGAN and MSGAN? HOT 1
- This loss is very unstable
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 msgan.