Caffe研究实践三 ------训练测试

最新推荐文章于 2018-09-06 17:04:07 发布

cv.exp

最新推荐文章于 2018-09-06 17:04:07 发布

阅读量860

点赞数

CC 4.0 BY-SA版权

分类专栏： Deep Learning 文章标签： Caffe

本文链接：https://blog.youkuaiyun.com/forest_world/article/details/51381715

Deep Learning 专栏收录该内容

172 篇文章

订阅专栏

本文详细介绍了如何使用Caffe框架训练CIFAR-10数据集，并通过一系列脚本操作实现了数据下载、转换和创建LMDB数据库的过程。最后，通过`train_quick.sh`脚本进行快速训练，展示了Caffe在计算机视觉任务中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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’

这里写图片描述

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

这里写图片描述

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

这里写图片描述