search

pluskid / Mocha.jl

Deep Learning framework for Julia
Other
1.29k stars 254 forks source link

Freeze Layer Parameters #31

Closed pluskid closed 9 years ago

pluskid commented 9 years ago

Part of #29. Provide Ability to freeze some layers in the net. This is useful for bottom-up layer-wise pre-training. The user could freeze the lower trained layer and train only the top layer.

coveralls commented 9 years ago

Coverage Status

Coverage increased (+0.0%) when pulling 18e5f6db796a3adced7388984960ce734968dcfc on dA into 9b4bd0c6d42279857a635b133d5ab0feb664e875 on master.