首先，導入必要的庫

import numpy as np
import matplotlib.pyplot as plt
import os,sys,caffe
%matplotlib inline

caffe_root='/home/lee/caffe/'
os.chdir(caffe_root)
sys.path.insert(0,caffe_root+'python')

plt.rcParams['figure.figsize'] = (8, 8)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

 　　　　　　設置網絡模型，並顯示該模型中各層名稱和參數的規模（注意此處是net.params, 而不是net.blobs)

net = caffe.Net(caffe_root + 'examples/cifar10/cifar10_full.prototxt',
                caffe_root + 'examples/cifar10/my_iter_10000.caffemodel',
                caffe.TEST)
[(k, v[0].data.shape) for k, v in net.params.items()]

[('conv1', (32, 3, 5, 5)),
 ('conv2', (32, 32, 5, 5)),
 ('conv3', (64, 32, 5, 5)),
 ('ip1', (10, 1024))]

 　　　　　　　　cifar10訓練的模型配置在文件cifar10_full.prototxt裏面，共有三個卷積層和一個全連接層，參數規模如上所示。

#編寫一個函數，用於顯示各層的參數
def show_feature(data, padsize=1, padval=0):
    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)
    data = np.pad(data, padding, mode='constant', constant_values=(padval, padval))
    
    # 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)
    plt.axis('off')

# 第一個卷積層，參數規模爲(32,3,5,5)，即32個5*5的3通道filter
weight = net.params["conv1"][0].data
print weight.shape
show_feature(weight.transpose(0, 2, 3, 1))

(32, 3, 5, 5)
參數有兩種類型：權值參數和偏置項。分別用params["conv1"][0] 和params["conv1"][1] 表示 。
我們只顯示權值參數，因此用params["conv1"][0] 

 

# 第二個卷積層的權值參數，共有32*32個filter,每個filter大小爲5*5
weight = net.params["conv2"][0].data
print weight.shape
show_feature(weight.reshape(32**2, 5, 5))

(32, 32, 5, 5)

# 第三個卷積層的權值，共有64*32個filter,每個filter大小爲5*5，取其前1024個進行可視化

 weight = net.params["conv3"][0].data print weight.shape show_feature(weight.reshape(64*32, 5, 5)[:1024])

(64, 32, 5, 5)