Caffe 코드 가이드(4): 데이터 세트 준비

Caffe에는 두 가지 간단한 예가 있는데 그것이 바로 MNIST와CIFAR-10이다. 전자는 손으로 쓴 디지털 식별에 사용되고 후자는 작은 그림 분류에 사용된다.이 두 데이터 세트는 Caffe 소스 프레임에서 스크립트(CAFFE ROOT/data/mnist/get mnist.sh 및 CAFFE ROOT/data/cifar10/get cifar10.sh)로 다운로드할 수 있습니다. 다음 그림과 같습니다.

$ ./get_cifar10.sh
Downloading...
--2014-12-02 01:20:12--  http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz
Resolving www.cs.toronto.edu... 128.100.3.30
Connecting to 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”


100%[===========================================================================================================================================================>] 170,052,171  859K/s   in 2m 16s


2014-12-02 01:22:28 (1.20 MB/s) - “cifar-10-binary.tar.gz” saved [170052171/170052171]


Unzipping...
Done.
$ ls
batches.meta.txt  data_batch_1.bin  data_batch_2.bin  data_batch_3.bin  data_batch_4.bin  data_batch_5.bin  get_cifar10.sh  readme.html  test_batch.bin

$ ./get_mnist.sh
Downloading...
--2014-12-02 01:24:25--  http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 9912422 (9.5M) [application/x-gzip]
Saving to: “train-images-idx3-ubyte.gz”


100%[===========================================================================================================================================================>] 9,912,422   2.09M/s   in 6.7s


2014-12-02 01:24:33 (1.42 MB/s) - “train-images-idx3-ubyte.gz” saved [9912422/9912422]


--2014-12-02 01:24:33--  http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 28881 (28K) [application/x-gzip]
Saving to: “train-labels-idx1-ubyte.gz”


100%[===========================================================================================================================================================>] 28,881      42.0K/s   in 0.7s


2014-12-02 01:24:34 (42.0 KB/s) - “train-labels-idx1-ubyte.gz” saved [28881/28881]


--2014-12-02 01:24:34--  http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1648877 (1.6M) [application/x-gzip]
Saving to: “t10k-images-idx3-ubyte.gz”


100%[===========================================================================================================================================================>] 1,648,877    552K/s   in 2.9s


2014-12-02 01:24:39 (552 KB/s) - “t10k-images-idx3-ubyte.gz” saved [1648877/1648877]


--2014-12-02 01:24:39--  http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 4542 (4.4K) [application/x-gzip]
Saving to: “t10k-labels-idx1-ubyte.gz”


100%[===========================================================================================================================================================>] 4,542       19.8K/s   in 0.2s


2014-12-02 01:24:40 (19.8 KB/s) - “t10k-labels-idx1-ubyte.gz” saved [4542/4542]


Unzipping...
Done.
$ ls
get_mnist.sh  t10k-images-idx3-ubyte  t10k-labels-idx1-ubyte  train-images-idx3-ubyte  train-labels-idx1-ubyte

만약 다운로드에 문제가 생기면 나의 자원에서 얻을 수 있습니다. 사이트 주소http://download.csdn.net/detail/kkk584520/8213463.
원본 데이터 집합이 이진 파일로 되어 있으며, leveldb나lmdb로 변환해야 Caffe가 식별할 수 있습니다.변환 도구는 Caffe 코드에 통합되어 있으며 CAFFE 참조ROOT/examples/mnist/convert_mnist_data.cpp
및 CAFFEROOT/examples/cifar10/convert_cifar_data.cpp, leveldb나lmdb 조작에 익숙하지 않으면 이 두 소스 코드에서 배울 수 있습니다.저희는 CAFFE에서...ROOT 디렉토리에서 두 가지 명령을 실행하면 됩니다.
./examples/mnist/create_mnist.sh
./examples/cifar10/create_cifar10.sh