nuclearboy95 / anomaly-detection-ocgan-tensorflow Goto Github PK
View Code? Open in Web Editor NEWTensorflow implementation of OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
Tensorflow implementation of OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
I need to learn more about how to use this package. Is there any documentation available or examples that explain how to use this package?
I need to use this code for tensorflow v2. Is there any way to make it compatible?
Could you please share the reproducing codes as an example using your 'ocgan' library?
First off great code! It's awesome you went through the time to reproduce the code of such a complex architecture.
This may be a product of my lack of understanding of python/tensorflow, but I can't seem to figure out how to isolate and save the classifier neural network. Your OCGAN can evaluate an anomaly score, but how can I access the classifier that produced it?
I think this would be a common interest for anyone trying to save networks for later evaluation.
This would also be useful for my research!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.