# Caffe学习系列(17)：模型各层数据和参数可视化

cifar10的各层数据和参数可视化

In [1]:
#加载必要的库
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import sys,os,caffe
In [2]:
#设置当前目录，判断模型是否训练好
caffe_root = '/home/bnu/caffe/'
sys.path.insert(0, caffe_root + 'python')
os.chdir(caffe_root)
if not os.path.isfile(caffe_root + 'examples/cifar10/cifar10_quick_iter_4000.caffemodel'):
print("caffemodel is not exist...")
In [3]:
#利用提前训练好的模型，设置测试网络
caffe.set_mode_gpu()
net = caffe.Net(caffe_root + 'examples/cifar10/cifar10_quick.prototxt',
caffe_root + 'examples/cifar10/cifar10_quick_iter_4000.caffemodel',
caffe.TEST)
In [4]:
net.blobs['data'].data.shape
Out[4]:
(1, 3, 32, 32)
In [5]:
#加载测试图片，并显示
print im.shape
plt.imshow(im)
plt.axis('off')
(32, 32, 3)

Out[5]:
(-0.5, 31.5, 31.5, -0.5)

In [6]:
#　编写一个函数，将二进制的均值转换为python的均值
def convert_mean(binMean,npyMean):
blob = caffe.proto.caffe_pb2.BlobProto()
blob.ParseFromString(bin_mean)
arr = np.array( caffe.io.blobproto_to_array(blob) )
npy_mean = arr[0]
np.save(npyMean, npy_mean )
binMean=caffe_root+'examples/cifar10/mean.binaryproto'
npyMean=caffe_root+'examples/cifar10/mean.npy'
convert_mean(binMean,npyMean)
In [7]:
#将图片载入blob中,并减去均值
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1)) ##格式转换为(cannel,weight,high)
transformer.set_raw_scale('data', 255)
transformer.set_channel_swap('data', (2,1,0))
net.blobs['data'].data[...] = transformer.preprocess('data',im) #输入数据传给data层
inputData=net.blobs['data'].data
In [8]:
#显示减去均值前后的数据
plt.figure()
plt.subplot(1,2,1),plt.title("origin")
plt.imshow(im)
plt.axis('off')
plt.subplot(1,2,2),plt.title("subtract mean")
plt.imshow(transformer.deprocess('data', inputData[0]))
plt.axis('off')
Out[8]:
(-0.5, 31.5, 31.5, -0.5)

In [9]:
#运行测试模型，并显示各层数据信息
net.forward()
[(k, v.data.shape) for k, v in net.blobs.items()]
Out[9]:
[('data', (1, 3, 32, 32)),
('conv1', (1, 32, 32, 32)),
('pool1', (1, 32, 16, 16)),
('conv2', (1, 32, 16, 16)),
('pool2', (1, 32, 8, 8)),
('conv3', (1, 64, 8, 8)),
('pool3', (1, 64, 4, 4)),
('ip1', (1, 64)),
('ip2', (1, 10)),
('prob', (1, 10))]
In [10]:
#显示各层的参数信息
[(k, v[0].data.shape) for k, v in net.params.items()]
Out[10]:
[('conv1', (32, 3, 5, 5)),
('conv2', (32, 32, 5, 5)),
('conv3', (64, 32, 5, 5)),
('ip1', (64, 1024)),
('ip2', (10, 64))]
In [11]:
#　编写一个函数，用于显示各层数据
data -= data.min()
data /= data.max()

# 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, padsize), (0, padsize)) + ((0, 0),) * (data.ndim - 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)))
data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
plt.figure()
plt.imshow(data,cmap='gray')
plt.axis('off')
plt.rcParams['figure.figsize'] = (8, 8)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
In [12]:
#显示第一个卷积层的输出数据和权值（filter）
#conv1_data = net.blobs['conv1'].data #返回conv1层的数据，net.blobs['conv1'].data[0]返回conv1层的数据的第一张图片
show_data(net.blobs['conv1'].data[0])
print net.blobs['conv1'].data.shape
show_data(net.params['conv1'][0].data.reshape(32*3,5,5))
print net.params['conv1'][0].data.shape
(1, 32, 32, 32)
(32, 3, 5, 5)


In [13]:
#显示第一次pooling后的输出数据
show_data(net.blobs['pool1'].data[0])
net.blobs['pool1'].data.shape
Out[13]:
(1, 32, 16, 16)

In [14]:
#显示第二次卷积后的输出数据以及相应的权值（filter）
print net.blobs['conv2'].data.shape
show_data(net.params['conv2'][0].data.reshape(32**2,5,5))
print net.params['conv2'][0].data.shape
(1, 32, 16, 16)
(32, 32, 5, 5)


In [15]:
#显示第三次卷积后的输出数据以及相应的权值（filter）,取前１024个进行显示
print net.blobs['conv3'].data.shape
show_data(net.params['conv3'][0].data.reshape(64*32,5,5)[:1024])
print net.params['conv3'][0].data.shape
(1, 64, 8, 8)
(64, 32, 5, 5)


In [16]:
#显示第三次池化后的输出数据
print net.blobs['pool3'].data.shape
(1, 64, 4, 4)


In [17]:
# 最后一层输入属于某个类的概率
feat = net.blobs['prob'].data[0]
print feat
plt.plot(feat.flat)
[  5.21440245e-03   1.58397834e-05   3.71246301e-02   2.28459597e-01
1.08315737e-03   7.17785358e-01   1.91939052e-03   7.67927198e-03
6.13298907e-04   1.05107691e-04]

Out[17]:
[<matplotlib.lines.Line2D at 0x7f3d882b00d0>]

airplane、automobile、bird、cat、deer、dog、frog、horse、ship、truck