Comments (5)
Hi, thanks for your question.
There are not bugs. First, you could use zip instead of itertools.izip (maybe you are asking this, it depends on your python version); Second, please make sure your dataset size can be divided exactly by the batch size .
Hope the above is helpful for you.
from espgan.
No, you misunderstood the usage of zip. The zip() function will only iterate over the smallest list passed. If given lists of different lengths, the resulting combination will only be as long as the smallest list passed.
from espgan.
Maybe you should check your data loader. You could check the data preparation in https://github.com/LynnHo/CycleGAN-Tensorflow-2/tree/v1. Or you could write your own data loader.
from espgan.
By the way, maybe you could check the length of "itertools.izip(a_loader, b_loader)". Also, the length of a_loader and b_loader.
I remember the training data size is 12,936, so the length of "itertools.izip(a_loader, b_loader)" should be 12936. In this case, the maximum of i is 12,935.
You could check your dataset loader code step by step. Good luck!
from espgan.
First, I have released this code for about 11 months. You are the first one to find a "bug". I think you could check your code step by step. We didn't meet your issue, how can we find a "bug". I don't think the bug is a friendly word for someone who releases her/his codes (but the issue is welcome).
Moreover, I mean you need to check your data path preparation. You need to make sure you put images into the right path. Again, check the path structure in https://github.com/LynnHo/CycleGAN-Tensorflow-2/tree/v1.
Last, I have given you some possible ways to find out the issue.
from espgan.
Related Issues (10)
- Release the code HOT 1
- code released HOT 1
- ModuleNotFoundError: No module named 'models.model_imagenet' HOT 3
- Is the train_A and test_A(train_B and test_B) are the same data in SPGAN? HOT 2
- the parameter is different with the tensorflow HOT 1
- How testing the re-ID performance HOT 1
- 一些关于 espgan and spgan区别的疑惑 HOT 4
- how many data!
- After running the program, the performance of the model decreases. HOT 1
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 espgan.