search

inoueakimitsu / milwrap

Wrapping single instance learning algorithms for fitting them to data for multiple instance learning
MIT License
1 stars 0 forks source link

Allow y to be initialized externally #6

Closed inoueakimitsu closed 2 years ago

inoueakimitsu commented 2 years ago

When using the current initialization process for y, the initial class cannot be assigned to an unusual class. This may cause learning to fail.

inoueakimitsu commented 2 years ago

7

Implemented an option to initialize y externally. The fit() method takes an initial_y argument. If initial_y is not given, the existing process will be executed. When initial_y is given, the initialization process is skipped.