使用caffe训练好的模型进行分类

最近在玩这个东西，按照网上的教程一步步的完成网络训练，但是却不知道该怎么使用。百度了一下还是没有确实连接的样子。可能这种问题实在太低级了哈。几乎可以说在官网上面有详细的说明。只是刚开始接触这个没有仔细看完吧。

首先关于适用caffe image-net如何训练的官方教程在：

http://caffe.berkeleyvision.org/gathered/examples/imagenet.html

认真看完，在该网站的最后有一个连接，介绍了如何使用训练好的模型(python版本)。

1 设置

1.1 设置python，numpy，matplotlib

# set up Python environment: numpy for numerical routines, and matplotlib for plotting
import numpy as np
import matplotlib.pyplot as plt
# display plots in this notebook
%matplotlib inline

# set display defaults
plt.rcParams['figure.figsize'] = (10, 10)        # large images
plt.rcParams['image.interpolation'] = 'nearest'  # don't interpolate: show square pixels
plt.rcParams['image.cmap'] = 'gray'  # use grayscale output rather than a (potentially misleading) color heatmap

1.2 导入 caffe

<span style="font-size:14px;"># The caffe module needs to be on the Python path;
#  we'll add it here explicitly.
import sys
caffe_root = '../'  # this file should be run from {caffe_root}/examples (otherwise change this line)
sys.path.insert(0, caffe_root + 'python')

import caffe
# If you get "No module named _caffe", either you have not built pycaffe or you have the wrong path.</span>

1.3 其它

如果需要的话可以下载参考模型("CaffeNet", AlexNet的一个变体)

import os
if os.path.isfile(caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'):
    print 'CaffeNet found.'
else:
    print 'Downloading pre-trained CaffeNet model...'
    !../scripts/download_model_binary.py ../models/bvlc_reference_caffenet

2 导入网络以及设置输入预处理

2.1 设置caffe为CPU模式，并导入网络模型

caffe.set_mode_cpu()

model_def = caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt'
model_weights = caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'

net = caffe.Net(model_def,      # defines the structure of the model
                model_weights,  # contains the trained weights
                caffe.TEST)     # use test mode (e.g., don't perform dropout)

2.2 设置输入预处理

官网使用的是caffe的caffe.io.Transformer来做这个事情。但是这个步骤与caffe的其他部分是独立的，所以这里使用别的方式来做预处理也可以。

官方的CaffeNet默认配置的是BGR格式图片。Values are expected to start in the range [0, 255] and then have the mean ImageNet pixel value subtracted from them. 另外通道维(the channel dimension)通常作为第一维。

然而，matplotlib在载入图像时，RGB格式的取值范围是[0,1]，且通道维作为最后一维。所以这里需要做转换。

# load the mean ImageNet image (as distributed with Caffe) for subtraction
mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy')
mu = mu.mean(1).mean(1)  # average over pixels to obtain the mean (BGR) pixel values
print 'mean-subtracted values:', zip('BGR', mu)

# create transformer for the input called 'data'
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})

transformer.set_transpose('data', (2,0,1))  # move image channels to outermost dimension
transformer.set_mean('data', mu)            # subtract the dataset-mean value in each channel
transformer.set_raw_scale('data', 255)      # rescale from [0, 1] to [0, 255]
transformer.set_channel_swap('data', (2,1,0))  # swap channels from RGB to BGR

mean-subtracted values: [('B', 104.0069879317889), ('G', 116.66876761696767), ('R', 122.6789143406786)]

3 CPU分类

现在已经准备好执行分类了。即使只对一张图像进行分类，同样设置一个50的批量尺寸展示其批处理。

# set the size of the input (we can skip this if we're happy
#  with the default; we can also change it later, e.g., for different batch sizes)
net.blobs['data'].reshape(50,        # batch size
                          3,         # 3-channel (BGR) images
                          227, 227)  # image size is 227x227

载入一个图片，并执行之前设置的预处理

image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)

输出：

<matplotlib.image.AxesImage at 0x7f09693a8c90>

对其进行分类

# copy the image data into the memory allocated for the net
net.blobs['data'].data[...] = transformed_image

### perform classification
output = net.forward()

output_prob = output['prob'][0]  # the output probability vector for the first image in the batch

print 'predicted class is:', output_prob.argmax()

输出：

predicted class is: 281

这个网络给了我们一个概率向量；概率最高的就是第281类。是否正确呢？检测ImageNet标签

# load ImageNet labels
labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'
if not os.path.exists(labels_file):
    !../data/ilsvrc12/get_ilsvrc_aux.sh
    
labels = np.loadtxt(labels_file, str, delimiter='\t')

print 'output label:', labels[output_prob.argmax()]

输出：

output label: n02123045 tabby, tabby cat

说明正确了。但是想看看其它几个概率很大的分类呢？

# sort top five predictions from softmax output
top_inds = output_prob.argsort()[::-1][:5]  # reverse sort and take five largest items

print 'probabilities and labels:'
zip(output_prob[top_inds], labels[top_inds])

输出：

probabilities and labels:

[(0.31243637, 'n02123045 tabby, tabby cat'),
 (0.2379719, 'n02123159 tiger cat'),
 (0.12387239, 'n02124075 Egyptian cat'),
 (0.10075711, 'n02119022 red fox, Vulpes vulpes'),
 (0.070957087, 'n02127052 lynx, catamount')]

4 转换到GPU模式

看看这个分类花了多久，和GPU模式做一个比较

%timeit net.forward()

1 loop, best of 3: 1.42 s per loop

即使是50个图的批处理，也只是一会的功夫。那么GPU模式呢？

caffe.set_device(0)  # if we have multiple GPUs, pick the first one
caffe.set_mode_gpu()
net.forward()  # run once before timing to set up memory
%timeit net.forward()

10 loops, best of 3: 70.2 ms per loop