Comments (2)
Hi, good question. From the theoretical point of view the only assumption for the FID is that the activations of the Inception coding layer (last 2048 dim pooling layer) are Gaussian distributed given your data. Then the FID calculates the squared Wasserstein-2 distance between the Gaussians of the activations of the real and generated data. From a practical point of view i suggest that also medical images produce near Gaussian activations, near enough such that both distributions, real and generated) can be compared.
from ttur.
Hello martin! The work is very great.But i want to consult whether FID can be used in medical image field? After all,Iception mode is trained on natural images.Thank you very much!
Hello, I am a student and I have the same problem as you. Have you solved the problem of calculating FID for medical images?
from ttur.
Related Issues (20)
- Problem using image dataset already in numpy format HOT 1
- ValueError: setting an array element with a sequence. HOT 3
- FID for GAN trained on MNIST HOT 4
- Is the calculation of covariance wrong?such as sigma = np.cov(act, rowvar=False)? HOT 4
- Inception score for cifar10 HOT 2
- should fid.py mention np.float64 ?
- I trained my GAN on cifar-10 (height,weight=32*32), and got FID=51. Should I resize the image to 64*64? HOT 1
- Why do I always encounter the error: 'ValueError: Imaginary component 89928690.58258057' HOT 15
- Variable not defined when running --lowprofile flag and reshape to batch_size issue
- The state file calculated with precalc_stats_example.py is sinificantly different with the one given on your websites?
- Where are images resized? HOT 2
- Invalid argument: activation input is not finite. : Tensor had NaN values HOT 1
- FID between a dataset and a single sample
- Some times get Imaginary component HOT 3
- ValueError: setting an array element with a sequence. HOT 2
- KeyError: "The name 'FID_Inception_Net/pool_3:0' refers to a Tensor which does not exist. The operation, 'FID_Inception_Net/pool_3', does not exist in the graph." HOT 3
- Can FID returns a negative number? HOT 2
- Number of real samples
- fid.py is always killed on Linux? 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 ttur.