Caffe研究实践 三

learning@learning-virtual-machine:~/caffe/data/cifar10$ ls

learning@learning-virtual-machine:~/caffe/data/cifar10$ ./get_cifar10.sh
Downloading…
–2016-05-12 10:03:45– http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz
Resolving www.cs.toronto.edu (www.cs.toronto.edu)… 128.100.3.30
Connecting to www.cs.toronto.edu (www.cs.toronto.edu)|128.100.3.30|:80… connected.
HTTP request sent, awaiting response… 200 OK
Length: 170052171 (162M) [application/x-gzip]
Saving to: ‘cifar-10-binary.tar.gz’

learning@learning-virtual-machine:~/caffe$ ./examples/cifar10/create_cifar10.sh
Creating lmdb…
I0512 10:09:58.590281 3878 db_lmdb.cpp:35] Opened lmdb examples/cifar10/cifar10_train_lmdb
I0512 10:09:58.591330 3878 convert_cifar_data.cpp:52] Writing Training data
I0512 10:09:58.591449 3878 convert_cifar_data.cpp:55] Training Batch 1

learning@learning-virtual-machine:~/caffe/examples/cifar10$ ls
cifar10_full.prototxt
cifar10_full_sigmoid_solver_bn.prototxt
cifar10_full_sigmoid_solver.prototxt
cifar10_full_sigmoid_train_test_bn.prototxt
cifar10_full_sigmoid_train_test.prototxt
cifar10_full_solver_lr1.prototxt
cifar10_full_solver_lr2.prototxt
cifar10_full_solver.prototxt
cifar10_full_train_test.prototxt
cifar10_quick.prototxt
cifar10_quick_solver_lr1.prototxt
cifar10_quick_solver.prototxt
cifar10_quick_train_test.prototxt
cifar10_test_lmdb
cifar10_train_lmdb
convert_cifar_data.cpp
create_cifar10.sh
mean.binaryproto
readme.md
train_full.sh
train_full_sigmoid_bn.sh
train_full_sigmoid.sh
train_quick.sh**重点内容**

训练
learning@learning-virtual-machine:~/caffe$ ./examples/cifar10/train_quick.sh

train_quick.sh代码：

#!/usr/bin/env sh 
TOOLS=./build/tools

$TOOLS/caffe train \
  --solver=examples/cifar10/cifar10_quick_solver.prototxt

# reduce learning rate by factor of 10 after 8 epochs
$TOOLS/caffe train \
  --solver=examples/cifar10/cifar10_quick_solver_lr1.prototxt \
  --snapshot=examples/cifar10/cifar10_quick_iter_4000.solverstate.h5

待续，深入研究分析

参考资料：
读书笔记 薛开宇