Mill.jl (Multiple Instance Learning Library) is a library built on top of Flux.jl aimed to flexibly prototype hierarchical multiple instance learning models as described in [1], [2] and [3]. It is developed to be:
- flexible and versatile
- as general as possible
- fast
- and dependent on only handful of other packages
Watch our introductory talk from JuliaCon 2021.
Installation
Run the following in REPL:
] add MillJulia v1.9 or later is required.
Getting started
For the quickest start, see the Musk example.
- Motivation: a brief introduction into the philosophy of
Mill.jl - Manual: a brief tutorial into
Mill.jl - Examples: some examples of
Mill.jluse - External tools: examples of integration with other packages
- Public API: extensive API reference
- References: related literature
- Citation: preferred citation entries