使用训练好的googlenet caffemodel进行图片分类

[TOC]

requisite：
1. ubuntu16.04，caffe已成功安装
2. python2.7
3. 我本地的caffe_root: /home/sarahzhou/caffe

下载googlenet caffemodel文件

有两种途径可以获取caffemodel文件：

1 使用caffe提供的脚本，注意在caffe_root下执行

sarahzhou@lenovo:~/caffe$ sudo python scripts/download_model_binary.py models/bvlc_googlenet

脚本的详细使用说明请参考caffe官网的where to get trained models部分。脚本下载完毕的bvlc_googlenet.caffemodel存储在${caffe_root}/models/bvlc_googlenet目录下。

2 直接到berkeleyvision的网站下载
http://dl.caffe.berkeleyvision.org/，下载完毕后放到${caffe_root}/models/bvlc_googlenet目录下。

准备数据

因为我们使用的googlenet caffemodel是用imagenet训练好的，所以我们使用这个model的时候，也需要知道相关的imagenet的数据信息：

sarahzhou@lenovo:~/caffe$ ./data/ilsvrc12/get_ilsvrc_aux.sh 

执行完毕后，在${caffe_root}/data/ilsvrc12目录下多了以下这些文件：

det_synset_words.txt  imagenet.bet.pickle        synsets.txt             //imagenet数据类别的ID，共有1000个类别synset_words.txt        //类别ID和类别名字的对应关系imagenet_mean.binaryproto //imagenet数据均值train.txt               test.txt                val.txt   

python代码

用来做测试的图片是：

图片分类

# coding=utf-8import numpy as npimport matplotlib.pyplot as pltimport pylabfrom PIL import Imageimport caffecaffe_root = "/home/sarahzhou/caffe/"net_file = caffe_root + "models/bvlc_googlenet/deploy.prototxt"model = caffe_root + "models/bvlc_googlenet/bvlc_googlenet.caffemodel"caffe.set_mode_cpu()net = caffe.Net(net_file, model, caffe.TEST)image_mean = np.load(caffe_root + "python/caffe/imagenet/ilsvrc_2012_mean.npy").mean(1).mean(1)# print 'mean-subtracted values:', zip('RGB', image_mean)# 输出结果：mean-subtracted values: [('R', 104.0069879317889), ('G', 116.66876761696767), ('B', 122.6789143406786)]data_shape = net.blobs['data'].data.shape# print data_shape# 输出结果：(10, 3, 224, 224) batch_size:10  channels:3  height:224  weight:224transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})transformer.set_transpose('data', (2, 0, 1))transformer.set_mean('data', image_mean)transformer.set_raw_scale('data', 255)transformer.set_channel_swap('data', (2, 1, 0))image = caffe.io.load_image('/home/sarahzhou/software/mydogs/dog.jpg')transformed_image = transformer.preprocess('data', image)# plt.imshow(image)# pylab.show()net.blobs['data'].data[...] = transformed_imageoutput = net.forward()output_prob = output['prob'][0]print 'The predicted class is : ', output_prob.argmax()label_file = caffe_root + "data/ilsvrc12/synset_words.txt"labels = np.loadtxt(label_file, str, delimiter='\t')print 'The label is : ', labels[output_prob.argmax()]top_inds = output_prob.argsort()[::-1][:5]print 'probabilities and labels: ', zip(output_prob[top_inds], labels[top_inds])

输出结果为：

The predicted class is : 266
The label is : n02113712 miniature poodle
probabilities and labels: [(0.32076371, ‘n02113712 miniature poodle’), (0.15544809, ‘n02096051 Airedale, Airedale terrier’), (0.14952005, ‘n02102973 Irish water spaniel’), (0.11370797, ‘n02113624 toy poodle’), (0.04295243, ‘n02093991 Irish terrier’)]

可以看到利用googlenet的caffe model预测出有0.32076371的概率是 miniature poodle(迷你贵宾)

feature map 尺寸

for layer_name, feature_map in net.blobs.iteritems():    print layer_name + '\t' + str(feature_map.data.shape)

上段代码输出每层的名称，和该层输出的feature map尺寸，输入结果为：

data (10, 3, 224, 224)
conv1/7x7_s2 (10, 64, 112, 112)
pool1/3x3_s2 (10, 64, 56, 56)
pool1/norm1 (10, 64, 56, 56)
conv2/3x3_reduce (10, 64, 56, 56)
conv2/3x3 (10, 192, 56, 56)
conv2/norm2 (10, 192, 56, 56)
pool2/3x3_s2 (10, 192, 28, 28)
pool2/3x3_s2_pool2/3x3_s2_0_split_0 (10, 192, 28, 28)
pool2/3x3_s2_pool2/3x3_s2_0_split_1 (10, 192, 28, 28)
pool2/3x3_s2_pool2/3x3_s2_0_split_2 (10, 192, 28, 28)
pool2/3x3_s2_pool2/3x3_s2_0_split_3 (10, 192, 28, 28)
inception_3a/1x1 (10, 64, 28, 28)
inception_3a/3x3_reduce (10, 96, 28, 28)
inception_3a/3x3 (10, 128, 28, 28)
inception_3a/5x5_reduce (10, 16, 28, 28)
inception_3a/5x5 (10, 32, 28, 28)
inception_3a/pool (10, 192, 28, 28)
inception_3a/pool_proj (10, 32, 28, 28)
inception_3a/output (10, 256, 28, 28)
inception_3a/output_inception_3a/output_0_split_0 (10, 256, 28, 28)
inception_3a/output_inception_3a/output_0_split_1 (10, 256, 28, 28)
inception_3a/output_inception_3a/output_0_split_2 (10, 256, 28, 28)
inception_3a/output_inception_3a/output_0_split_3 (10, 256, 28, 28)
inception_3b/1x1 (10, 128, 28, 28)
inception_3b/3x3_reduce (10, 128, 28, 28)
inception_3b/3x3 (10, 192, 28, 28)
inception_3b/5x5_reduce (10, 32, 28, 28)
inception_3b/5x5 (10, 96, 28, 28)
inception_3b/pool (10, 256, 28, 28)
inception_3b/pool_proj (10, 64, 28, 28)
inception_3b/output (10, 480, 28, 28)
pool3/3x3_s2 (10, 480, 14, 14)
pool3/3x3_s2_pool3/3x3_s2_0_split_0 (10, 480, 14, 14)
pool3/3x3_s2_pool3/3x3_s2_0_split_1 (10, 480, 14, 14)
pool3/3x3_s2_pool3/3x3_s2_0_split_2 (10, 480, 14, 14)
pool3/3x3_s2_pool3/3x3_s2_0_split_3 (10, 480, 14, 14)
inception_4a/1x1 (10, 192, 14, 14)
inception_4a/3x3_reduce (10, 96, 14, 14)
inception_4a/3x3 (10, 208, 14, 14)
inception_4a/5x5_reduce (10, 16, 14, 14)
inception_4a/5x5 (10, 48, 14, 14)
inception_4a/pool (10, 480, 14, 14)
inception_4a/pool_proj (10, 64, 14, 14)
inception_4a/output (10, 512, 14, 14)
inception_4a/output_inception_4a/output_0_split_0 (10, 512, 14, 14)
inception_4a/output_inception_4a/output_0_split_1 (10, 512, 14, 14)
inception_4a/output_inception_4a/output_0_split_2 (10, 512, 14, 14)
inception_4a/output_inception_4a/output_0_split_3 (10, 512, 14, 14)
inception_4b/1x1 (10, 160, 14, 14)
inception_4b/3x3_reduce (10, 112, 14, 14)
inception_4b/3x3 (10, 224, 14, 14)
inception_4b/5x5_reduce (10, 24, 14, 14)
inception_4b/5x5 (10, 64, 14, 14)
inception_4b/pool (10, 512, 14, 14)
inception_4b/pool_proj (10, 64, 14, 14)
inception_4b/output (10, 512, 14, 14)
inception_4b/output_inception_4b/output_0_split_0 (10, 512, 14, 14)
inception_4b/output_inception_4b/output_0_split_1 (10, 512, 14, 14)
inception_4b/output_inception_4b/output_0_split_2 (10, 512, 14, 14)
inception_4b/output_inception_4b/output_0_split_3 (10, 512, 14, 14)
inception_4c/1x1 (10, 128, 14, 14)
inception_4c/3x3_reduce (10, 128, 14, 14)
inception_4c/3x3 (10, 256, 14, 14)
inception_4c/5x5_reduce (10, 24, 14, 14)
inception_4c/5x5 (10, 64, 14, 14)
inception_4c/pool (10, 512, 14, 14)
inception_4c/pool_proj (10, 64, 14, 14)
inception_4c/output (10, 512, 14, 14)
inception_4c/output_inception_4c/output_0_split_0 (10, 512, 14, 14)
inception_4c/output_inception_4c/output_0_split_1 (10, 512, 14, 14)
inception_4c/output_inception_4c/output_0_split_2 (10, 512, 14, 14)
inception_4c/output_inception_4c/output_0_split_3 (10, 512, 14, 14)
inception_4d/1x1 (10, 112, 14, 14)
inception_4d/3x3_reduce (10, 144, 14, 14)
inception_4d/3x3 (10, 288, 14, 14)
inception_4d/5x5_reduce (10, 32, 14, 14)
inception_4d/5x5 (10, 64, 14, 14)
inception_4d/pool (10, 512, 14, 14)
inception_4d/pool_proj (10, 64, 14, 14)
inception_4d/output (10, 528, 14, 14)
inception_4d/output_inception_4d/output_0_split_0 (10, 528, 14, 14)
inception_4d/output_inception_4d/output_0_split_1 (10, 528, 14, 14)
inception_4d/output_inception_4d/output_0_split_2 (10, 528, 14, 14)
inception_4d/output_inception_4d/output_0_split_3 (10, 528, 14, 14)
inception_4e/1x1 (10, 256, 14, 14)
inception_4e/3x3_reduce (10, 160, 14, 14)
inception_4e/3x3 (10, 320, 14, 14)
inception_4e/5x5_reduce (10, 32, 14, 14)
inception_4e/5x5 (10, 128, 14, 14)
inception_4e/pool (10, 528, 14, 14)
inception_4e/pool_proj (10, 128, 14, 14)
inception_4e/output (10, 832, 14, 14)
pool4/3x3_s2 (10, 832, 7, 7)
pool4/3x3_s2_pool4/3x3_s2_0_split_0 (10, 832, 7, 7)
pool4/3x3_s2_pool4/3x3_s2_0_split_1 (10, 832, 7, 7)
pool4/3x3_s2_pool4/3x3_s2_0_split_2 (10, 832, 7, 7)
pool4/3x3_s2_pool4/3x3_s2_0_split_3 (10, 832, 7, 7)
inception_5a/1x1 (10, 256, 7, 7)
inception_5a/3x3_reduce (10, 160, 7, 7)
inception_5a/3x3 (10, 320, 7, 7)
inception_5a/5x5_reduce (10, 32, 7, 7)
inception_5a/5x5 (10, 128, 7, 7)
inception_5a/pool (10, 832, 7, 7)
inception_5a/pool_proj (10, 128, 7, 7)
inception_5a/output (10, 832, 7, 7)
inception_5a/output_inception_5a/output_0_split_0 (10, 832, 7, 7)
inception_5a/output_inception_5a/output_0_split_1 (10, 832, 7, 7)
inception_5a/output_inception_5a/output_0_split_2 (10, 832, 7, 7)
inception_5a/output_inception_5a/output_0_split_3 (10, 832, 7, 7)
inception_5b/1x1 (10, 384, 7, 7)
inception_5b/3x3_reduce (10, 192, 7, 7)
inception_5b/3x3 (10, 384, 7, 7)
inception_5b/5x5_reduce (10, 48, 7, 7)
inception_5b/5x5 (10, 128, 7, 7)
inception_5b/pool (10, 832, 7, 7)
inception_5b/pool_proj (10, 128, 7, 7)
inception_5b/output (10, 1024, 7, 7)
pool5/7x7_s1 (10, 1024, 1, 1)
loss3/classifier (10, 1000)
prob (10, 1000)

从上述输出结果中就可以看出每层经过运算之后输出到下一层的数据尺寸，比如inception_4b/3x3 (10, 224, 14, 14)，其中batch_size:10 channels:224 height:14 weight:14.

卷积核尺寸

for layer_name, kernel in net.params.iteritems():    print layer_name + '\t' + str(kernel[0].data.shape)

上述代码用来输出每层的卷积核的尺寸：

conv1/7x7_s2 (64, 3, 7, 7)
conv2/3x3_reduce (64, 64, 1, 1)
conv2/3x3 (192, 64, 3, 3)
inception_3a/1x1 (64, 192, 1, 1)
inception_3a/3x3_reduce (96, 192, 1, 1)
inception_3a/3x3 (128, 96, 3, 3)
inception_3a/5x5_reduce (16, 192, 1, 1)
inception_3a/5x5 (32, 16, 5, 5)
inception_3a/pool_proj (32, 192, 1, 1)
inception_3b/1x1 (128, 256, 1, 1)
inception_3b/3x3_reduce (128, 256, 1, 1)
inception_3b/3x3 (192, 128, 3, 3)
inception_3b/5x5_reduce (32, 256, 1, 1)
inception_3b/5x5 (96, 32, 5, 5)
inception_3b/pool_proj (64, 256, 1, 1)
inception_4a/1x1 (192, 480, 1, 1)
inception_4a/3x3_reduce (96, 480, 1, 1)
inception_4a/3x3 (208, 96, 3, 3)
inception_4a/5x5_reduce (16, 480, 1, 1)
inception_4a/5x5 (48, 16, 5, 5)
inception_4a/pool_proj (64, 480, 1, 1)
inception_4b/1x1 (160, 512, 1, 1)
inception_4b/3x3_reduce (112, 512, 1, 1)
inception_4b/3x3 (224, 112, 3, 3)
inception_4b/5x5_reduce (24, 512, 1, 1)
inception_4b/5x5 (64, 24, 5, 5)
inception_4b/pool_proj (64, 512, 1, 1)
inception_4c/1x1 (128, 512, 1, 1)
inception_4c/3x3_reduce (128, 512, 1, 1)
inception_4c/3x3 (256, 128, 3, 3)
inception_4c/5x5_reduce (24, 512, 1, 1)
inception_4c/5x5 (64, 24, 5, 5)
inception_4c/pool_proj (64, 512, 1, 1)
inception_4d/1x1 (112, 512, 1, 1)
inception_4d/3x3_reduce (144, 512, 1, 1)
inception_4d/3x3 (288, 144, 3, 3)
inception_4d/5x5_reduce (32, 512, 1, 1)
inception_4d/5x5 (64, 32, 5, 5)
inception_4d/pool_proj (64, 512, 1, 1)
inception_4e/1x1 (256, 528, 1, 1)
inception_4e/3x3_reduce (160, 528, 1, 1)
inception_4e/3x3 (320, 160, 3, 3)
inception_4e/5x5_reduce (32, 528, 1, 1)
inception_4e/5x5 (128, 32, 5, 5)
inception_4e/pool_proj (128, 528, 1, 1)
inception_5a/1x1 (256, 832, 1, 1)
inception_5a/3x3_reduce (160, 832, 1, 1)
inception_5a/3x3 (320, 160, 3, 3)
inception_5a/5x5_reduce (32, 832, 1, 1)
inception_5a/5x5 (128, 32, 5, 5)
inception_5a/pool_proj (128, 832, 1, 1)
inception_5b/1x1 (384, 832, 1, 1)
inception_5b/3x3_reduce (192, 832, 1, 1)
inception_5b/3x3 (384, 192, 3, 3)
inception_5b/5x5_reduce (48, 832, 1, 1)
inception_5b/5x5 (128, 48, 5, 5)
inception_5b/pool_proj (128, 832, 1, 1)
loss3/classifier (1000, 1024)

卷积核和feature map的可视图

def vis_square(data):    # normalize data for display    data = (data - data.min()) / (data.max() - data.min())    # force the number of filters to be square    n = int(np.ceil(np.sqrt(data.shape[0])))    padding = (((0, n ** 2 - data.shape[0]),                (0, 1), (0, 1))  # add some space between filters               + ((0, 0),) * (data.ndim - 3))  # don't pad the last dimension (if there is one)    data = np.pad(data, padding, mode='constant', constant_values=1)  # pad with ones (white)    # tile the filters into an image    data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])    plt.imshow(data);    pylab.show()    plt.axis('off')

filters = net.params['conv1/7x7_s2'][0].datavis_square(filters.transpose(0, 2, 3, 1))feat = net.blobs['conv1/7x7_s2'].data[0, :36]vis_square(feat)

http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/00-classification.ipynb