caffe下数据可视化

最新推荐文章于 2019-02-13 18:19:50 发布

原创最新推荐文章于 2019-02-13 18:19:50 发布 · 1k 阅读

1 ·

CC 4.0 BY-SA版权

caffe 专栏收录该内容

8 篇文章

订阅专栏

本文主要学习caffe官网例子Classification: Instant Recognition with Caffe，采用caffe数据可视化的总结．

其主要过程包括：

１）　定义图像窗口属性
２）　下载caffe模型，调用caffe.Net网络载入模型配置，模型权值，模型测试
３）　数据转化，变换通道，去除均值，变换尺寸，变换rgb...
４）　定义输入图像大小批次，载入图像，并做预处理
５）　执行前向传播，预测图像类别，载入标签做对比
６）　输出每层输入数据的维度，权值偏值的维度
７）　定义可视化函数，对卷积输入，激活输出可视化
８）　载入自己数据对输出做预测

１）　定义图像窗口属性

# 1) setup
# 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
import time
# set display defaults
plt.rcParams['figure.figsize'] = (10, 10)        # large images (width,height)　窗口大小(inches)
plt.rcParams['image.interpolation'] = 'nearest'  # don't interpolate: show square pixels
plt.rcParams['image.cmap'] = 'gray'  # use grayscale output rather than a (potentially misleading)

２）下载caffe模型，调用caffe.Net网络载入模型配置，模型权值，模型测试# The caffe module needs to be on the Python path;

# The caffe module needs to be on the Python path;
#  we'll add it here explicitly.
import sys
caffe_root = '/home/cc/caffe-master/'  # this file should be run from {caffe_root}/examples (otherwise change this line)
# sys.path.insert(0, caffe_root + 'python')
#　可在/etc/profile文件下添加目录．以后调用不在插入．
 # sys.path.append(0,'/home/cc/caffe-master/python')

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

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

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'

#  caffe.Net.__init__(self, model_file, pretrained_file, caffe.TEST) 
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)

３）　数据转化，变换通道，去除均值，变换尺寸，变换rgb...

# 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})
# print net.blobs['data'].data.shape
transformer.set_transpose('data', (2, 0, 1))  # move image channels to outermost dimension
# changed the [ h, w, channel] to [channel, height, width]
# print net.blobs['data'].data.shape
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)]
# print net.blobs['data'].data.shape

４）　定义输入图像大小批次，载入图像，并做预处理

# 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

image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg') #(200,200,3)
# print image.shape  # (height,width,channel)
transformed_image = transformer.preprocess('data', image)#将输入图片转发为ｃａｆｆｅ格式
# print net.blobs['data'].data.shape  # (batches, channel,height,width)
plt.imshow(image)
# plt.show()

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

５）　执行前向传播，预测图像类别，载入标签做对比

# load ImageNet labels
### 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()  # 281

labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'if not os.path.exists(labels_file): # !../ data / ilsvrc12 / get_ilsvrc_aux.sh print 'not labels_file'labels = np.loadtxt(labels_file, str, delimiter='\t')# delimiter限定符默认空格# The characters or list of characters used to indicate the start of a comment; default: ‘#’.print 'output label:', labels[output_prob.argmax()] # n02123045 tabby, tabby cat#其它低一些的预测# sort top five predictions from softmax outputtop_inds = output_prob.argsort()[::-1][:5] # reverse sort and take five largest itemsprint "probabilities and labels:\n", zip(output_prob[top_inds], labels[top_inds])start_time = time.time()net.forward()print (time.time()-start_time)# 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# print (time.time()-start_time)

6)输出每层输入数据的维度，权值偏值的维度

# 6) 可视化 (batch_size,channel_dim,height,width)
# for each layer, show the output shape
for layer_name, blob in net.blobs.iteritems():
    print layer_name + '\t' + str(blob.data.shape)

# 输出结果对后面理解数据结构很重要：
#data    (50, 3, 227, 227)
#conv1    (50, 96, 55, 55)
#pool1    (50, 96, 27, 27)
#norm1    (50, 96, 27, 27)
#conv2    (50, 256, 27, 27)
#pool2    (50, 256, 13, 13)
#norm2    (50, 256, 13, 13)
#conv3    (50, 384, 13, 13)
#conv4    (50, 384, 13, 13)
#conv5    (50, 256, 13, 13)
#pool5    (50, 256, 6, 6)
#fc6    (50, 4096)
#fc7    (50, 4096)
#fc8    (50, 1000)
# prob    (50, 1000)

for layer_name, param in net.params.iteritems():
    print layer_name + '\t' + str(param[0].data.shape), str(param[1].data.shape)

# 输出结果对后面理解数据结构很重要：

#conv1   (96, 3, 11, 11) (96,)
#conv2   (256, 48, 5, 5) (256,)
#conv3   (384, 256, 3, 3) (384,)
#conv4   (384, 192, 3, 3) (384,)
#conv5   (256, 192, 3, 3) (256,)
#fc6   (4096, 9216) (4096,)
#fc7   (4096, 4096) (4096,)
#fc8   (1000, 4096) (1000,)

#7)定义可视化函数，对卷积输入，激活输出可视化

def vis_square(data):
    """Take an array of shape (n, height, width) or (n, height, width, 3)
       and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)"""

    # 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])))  #10  #96个滤波器组时
    padding = (((0, n ** 2 - data.shape[0]),  #((-,4),(0,1),(0,1),(0,0))
                (0, 1), (0, 1))  # add some space between filters #给(11,11)添加
               + ((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)
    # np.lib.pad(data,((3,2),(4,6)),,'minimum') #分别上下左右按照不同的数目来填充最小的数字
    print 'data,shape', data.shape     #(100,12,12,3)
    print 'data,shape1', data.shape[1:]  # (12,12,3)
    # 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)))
    # (0,2,1,3)+(4) =(0,2,1,3,4)
    # print data.shape　#(10,12,10,12,3)
    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
    # print 'data.shape2', data.shape   #(120,120,3)
    plt.imshow(data)
    plt.show()
    plt.axis('off')


# the parameters are a list of [weights, biases]
filters = net.params['conv1'][0].data 　#（９６，３，１１，１１）提取卷积核的数据；卷积后n = (227-(ker-sd))/sd=(227-(11-4))/4=55

vis_square(filters.transpose(0, 2, 3, 1)) #转换用于ｐｙｔｈｏｎ数据显示

# the first layer output[rectified responses of the filters above]
feat = net.blobs['conv1'].data[0, :36]　#(36,55,55),截取批次中第一个样本,36个filter可视化
＃conv1    (50, 96, 55, 55)
vis_square(feat)


# the fifth layer after pooling
feat = net.blobs['pool5'].data[0]
vis_square(feat)


#the first fully connetcted layer
feat = net.blobs['fc6'].data[0]
plt.subplot(2, 1, 1)
plt.plot(feat.flat)
plt.subplot(2, 1, 2)
plt.hist(feat.flat[feat.flat > 0], bins=100)
plt.show()

# the final probability output, prob
feat = net.blobs['prob'].data[0]
plt.figure(figsize=(15, 3))
plt.plot(feat.flat)

# 8) 载入自己数据对输出做预

# 运行自己的图像
# transform it and copy it into the net
ImagePath = '/home/cc/temp/'
for i in range(0, 20):
    image = caffe.io.load_image(ImagePath+'%s.jpg' %i)
    net.blobs['data'].data[...] = transformer.preprocess('data', image)

    # perform classification
    net.forward()

    # obtain the output probabilities
    output_prob = net.blobs['prob'].data[0]    #(1000,)

    # sort top five predictions from softmax output
    top_inds = output_prob.argsort()[::-1][:5]  #排列从小到大－－－［：：－１］反转从大到小－－［：５］截取前５个最大索引

    plt.imshow(image)
    plt.show()
    print "probabilities and labels:\n", zip(output_prob[top_inds], labels[top_inds])