Comments (5)
Hi, I have rewritten the code for calculating Inception Score, taking the first problem into consideration:https://github.com/tsc2017/inception-score
As to the second problem, since the softmax function hardly outputs a 0 for a category, which means the conditional and marginal distribution of y is supported on all the 1000 classes, it is unlikely to get a 0*log(0), log(∞) or divide-by-0 error, and I do not observe any numerical instability, neither with the old nor with my new implementation.
Lastly, since the inception score is approximated by a statistic of a sample, just make sure the sample size is big enough. The common use of 50000 images in 10 splits seems acceptable. Take the CIFAR-10 training set images as an example, the inception score is around 11.34 in 1 split and 11.31±0.08 if in 10 splits.
from improved-gan.
@lipanpeng https://arxiv.org/abs/1801.01973
@xunhuang1995 the third point is valid, because 5k splits might be too small to adequately represent 1k classes. And as they show in the paper, IS changes depending on the size of the split.
from improved-gan.
The first point is an important issue. For the third point, note that they do NOT intend to calculate the inception score (IS) for 50,000 inputs. Rather, they spit 50,000 samples into 10 splits each with 5,000 samples. They then calculate IS for each split and return the average IS over splits. So the code is correct.
from improved-gan.
So,which version is correct?
from improved-gan.
Can anyone tell me where can I find the material about the inception score?
from improved-gan.
Related Issues (20)
- Loss Functions: Paper vs Code HOT 1
- Variable does not exist or was not created with tf.get_variable
- loss about l_unl is not clear
- why not zero mean the input HOT 1
- Inception score for conditional GANs HOT 1
- Batch size mismatch with Inception classifier HOT 10
- how to specify num of classes or labels in imagenet code
- can't run it HOT 2
- Tab Error HOT 3
- ValueError: squeeze_dims[1] not in [-2,2). for 'Squeeze_1' (op: 'Squeeze') with input shapes: [?,2048]. HOT 1
- question of implementation of inception score HOT 7
- AttributeError: 'module' object has no attribute 'absolute_import' HOT 1
- how long train_mnist_feature_matching.py run?
- What version of your python
- Will historical averaging from the paper be implemented?
- Segmentation fault
- Implementation of cifar10_match_feature on Pytorch.
- What's the meaning of the parameter splits(default=10)?
- Inference mode vs training mode
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 improved-gan.