v0.4.0 Release Candidate 1

• Faster Generation of inference features
• Remove redundant samtools tview code
• Ability to handle multiple read types

v0.3.0

• New non-RLE model
• Updated documentation and benchmarks
• Bug fixes
• medaka_consensus no longer needs a pomoxis installation to run
• Dockerfile to build a medaka Docker image

v0.2.0

• Release with pre-trained model.
• Updated walkthrough and benchmarks.

v0.1.0

• Overhaul API
• Add walkthrough

v0.0.2

• Generate pileup using samtools tview.
• Updated default model architecture.
• Extensive package restructuring.
• New features.py with two example feature functions, making it easier for developers to experiment with their own features.

v0.0.1

First prerelease. Simple consensus network using pileup counts.