在数据量比较大的时候,往往采取多次降学习率进行训练。
例子中 cifar10 就用 traini_full .
#!/usr/bin/env sh
TOOLS=./build/tools
$TOOLS/caffe train \
--solver=examples/cifar10/cifar10_full_solver.prototxt
# reduce learning rate by factor of 10
$TOOLS/caffe train \
--solver=examples/cifar10/cifar10_full_solver_lr1.prototxt \
--snapshot=examples/cifar10/cifar10_full_iter_60000.solverstate
# reduce learning rate by factor of 10
$TOOLS/caffe train \
--solver=examples/cifar10/cifar10_full_solver_lr2.prototxt \
--snapshot=examples/cifar10/cifar10_full_iter_65000.solverstate