Siamese network embedding 该例子是利用Caffe完成Siamese网络的特征抽取和plotting的例子。本文为了运行于本机，只做了细微修改和中文说明，原始文件来源于Ca

Siamese network embedding

该例子是利用Caffe完成Siamese网络的特征抽取和plotting的例子。本文为了运行于本机，只做了细微修改和中文说明，原始文件来源于Caffe官网对应的Notebook Examples。http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/siamese/mnist_siamese.ipynb

---Last update 2015年6月7日

Setup

import numpy as npimport matplotlib.pyplot as plt%matplotlib inline# 切换工作目录到 caffe-master%cd '/home/ouxinyu/caffe-master'# Make sure that caffe is on the python path:caffe_root = './'  # this file is expected to be in {caffe_root}/examples/siameseimport syssys.path.insert(0, caffe_root + 'python')import caffe

/home/ouxinyu/caffe-master

下载训练数据并生成训练模型

要完成本例需要先完成Siamese的训练，具体细节参考Caffe官网文档：http://caffe.berkeleyvision.org/gathered/examples/siamese.html

# 如果没有下载mnist数据，请先下载，可以使用ssh运行，也可以直接在ipython notebook中运行# 需要联网才能完成下载# ~/caffe-master$ data/mnist/get_mnist.sh! data/mnist/get_mnist.sh

Downloading...--2015-06-07 18:17:34--  http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz正在解析主机 yann.lecun.com (yann.lecun.com)... 128.122.47.89正在连接 yann.lecun.com (yann.lecun.com)|128.122.47.89|:80... 已连接。已发出 HTTP 请求，正在等待回应... ^C

# ~/caffe-master$ examples/siamese/create_mnist_siamese.sh! examples/siamese/create_mnist_siamese.sh

Creating leveldb...Done.

#~/caffe-master$ examples/siamese/train_mnist_siamese.sh# 默认训练50000iter，大约5-10分钟! examples/siamese/train_mnist_siamese.sh

Load the trained net

MODEL_FILE = 'examples/siamese/mnist_siamese.prototxt'# decrease if you want to preview during trainingPRETRAINED_FILE = 'examples/siamese/mnist_siamese_iter_50000.caffemodel' caffe.set_mode_cpu()net = caffe.Net(MODEL_FILE, PRETRAINED_FILE, caffe.TEST)

Load MNIST test data

TEST_DATA_FILE = 'data/mnist/t10k-images-idx3-ubyte'TEST_LABEL_FILE = 'data/mnist/t10k-labels-idx1-ubyte'n = 10000with open(TEST_DATA_FILE, 'rb') as f:    f.read(16) # skip the header    raw_data = np.fromstring(f.read(n * 28*28), dtype=np.uint8)with open(TEST_LABEL_FILE, 'rb') as f:    f.read(8) # skip the header    labels = np.fromstring(f.read(n), dtype=np.uint8)

Generate the Siamese features

# reshape and preprocesscaffe_in = raw_data.reshape(n, 1, 28, 28) * 0.00390625 # manually scale data instead of using `caffe.io.Transformer`out = net.forward_all(data=caffe_in)

Visualize the learned Siamese embedding

feat = out['feat']f = plt.figure(figsize=(16,9))c = ['#ff0000', '#ffff00', '#00ff00', '#00ffff', '#0000ff',      '#ff00ff', '#990000', '#999900', '#009900', '#009999']for i in range(10):    plt.plot(feat[labels==i,0].flatten(), feat[labels==i,1].flatten(), '.', c=c[i])plt.legend(['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'])plt.grid()plt.show()