我是使用cmake的方法进行的caffe的编译，可以看我之前的博客。将caffe目录下的python文件夹中的caffe文件夹拷贝到python\Lib\site-packages路径下。然后在import caffe，出现的一般是升级之类的问题，按照要求解决就行了。
之后在spyder中就行模型的可视化。代码内容主要是依据caffe官方的教程而来，添加了mean文件的转化函数。对于自己的网络需要修改的参数部分。
`import numpy as np
import matplotlib.pyplot as plt
#%matplotlib inline
plt.rcParams[‘figure.figsize’] = (10, 10) # large images
plt.rcParams[‘image.interpolation’] = ‘nearest’ # 不插值：显示方形像素
plt.rcParams[‘image.cmap’] = ‘gray’ # 使用灰度输出
import sys
caffe_root = ‘E:/caffe’
sys.path.insert(0, caffe_root + ‘python’)
import caffe
# 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()
bin_mean = open(binMean, ‘rb’ ).read()
blob.ParseFromString(bin_mean)
arr = np.array( caffe.io.blobproto_to_array(blob) )
npy_mean = arr[0]
np.save(npyMean, npy_mean )
caffe.set_mode_cpu()
#以下参数根据实际情况进行修改
#model_def = caffe_root + ‘/models/bvlc_reference_caffenet/deploy.prototxt’
#model_weights = caffe_root + ‘/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel’
model_def = ‘/Inceptionv2/deploy.prototxt’
model_weights = ‘/googlenet2_4/bvlc_googlenet2_4_iter_18000.caffemodel’
#mu = np.load(caffe_root + ‘/python/caffe/imagenet/ilsvrc_2012_mean.npy’)
mu = np.load(’/data/mean.npy’)
image = caffe.io.load_image(caffe_root + ‘/examples/images/cat.jpg’)
#labels_file = caffe_root + ‘/data/ilsvrc12/synset_words.txt’
labels_file =’/data/label.txt’
net = caffe.Net(model_def,model_weights,caffe.TEST)
mu = mu.mean(1).mean(1) #平均像素值以获得平均（BGR）像素值
print ‘mean-subtracted values:’, zip(‘BGR’, mu)
#为称为“数据”的输入创建变换器
transformer = caffe.io.Transformer({‘data’: net.blobs[‘data’].data.shape})
#将图像通道移动到最外层
transformer.set_transpose(‘data’, (2,0,1))
transformer.set_mean(‘data’, mu)
transformer.set_raw_scale(‘data’, 255)
transformer.set_channel_swap(‘data’, (2,1,0))
#参数需要依据网络结构的输入变化而变化
net.blobs[‘data’].reshape(50, # batch size
3, # 3-channel (BGR) images
224, 224) # image size is 227x227
transformed_image = transformer.preprocess(‘data’, image)
plt.imshow(image)
#将图像数据复制到为网络分配的内存中
net.blobs[‘data’].data[…] = transformed_image
output = net.forward()
#网络名称依据大家.pro文件中的不同自行定义，下面的同样
output_prob = output[‘loss1/loss1’][0]
print ‘predicted class is:’, output_prob.argmax()
labels = np.loadtxt(labels_file, str, delimiter=’\t’)
print ‘output label:’, labels[output_prob.argmax()]
#((batch_size, channel_dim, height, width)
for layer_name, blob in net.blobs.iteritems():
print layer_name + ‘\t’ + str(blob.data.shape)
#(output_channels, input_channels, filter_height, filter_width)
for layer_name, param in net.params.iteritems():
print layer_name + ‘\t’ + str(param[0].data.shape), str(param[1].data.shape)
def vis_square(data):
data = (data - data.min()) / (data.max() - data.min())
#强制过滤器的数量为正方形
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)
#将过滤器平铺到图像中
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’)
filters = net.params[‘conv_conv1’][0].data
vis_square(filters.transpose(0, 2, 3, 1))
print’\n’
feat = net.blobs[‘conv1’].data[0, :36]
vis_square(feat)
#第一个完全连接层，fc6 我们显示正值的输出值和直方图
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)
feat = net.blobs[‘prob’].data[0]
plt.figure(figsize=(15, 3))
plt.plot(feat.flat)
`