-
GenerativeDenseUNet
Discontinued An RBF based artificial neural network used for the purpose of semantic image segmentation. The backbone of this model is a DenseUNet. The head of the convolutional neural network is an RBF layer. Inference can be done using Bayes Theorem, or Softmax.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
The flag images are all from from Wikipedia. The color compositions were calculated using Python by quantizing the images to red, white and blue (and ignoring the transparent areas in the case of Nepal). The ternary plot was generated using the python-ternary package.
You can add another a 4th axes which will give you a tetrahedron. Just like the ternary plot which embeds 3D data into a 2D plane, a tetrahedron will embed 4D data into a 3D volume. I’ve used this in my neural networks to visualize the 4D embedding space. I have an example of such a plot here https://github.com/jgcastro89/GenerativeDenseUNet
Related posts
-
Has anyone ever made pipers in R?
-
What's the best option for plotting ternary diagrams in Python? Is there a matplotlib solution?
-
What is the best practice for injecting configuration into a python application
-
Ask HN: Open-source, local Text-to-Speech (TTS) generators
-
Where do you get your B2B news?