caffe-python接口图片分类demo

文章转载自：
http://wentaoma.com/2016/08/10/caffe-python-common-api-reference/

图片分类

加载Model数据

net = caffe.Net(
        deploy_prototxt_path,   # 用于分类的网络定义文件路径
        caffe_model_path,       # 训练好模型路径
        caffe.TEST              # 设置为测试阶段
        )

中值文件转换

#　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()
    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 )
# 调用函数转换均值
binMean='examples/cifar10/mean.binaryproto'
npyMean='examples/cifar10/mean.npy'
convert_mean(binMean,npyMean)

图片预处理

# 设定图片的shape格式为网络data层格式
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
# 改变维度的顺序，由原始图片维度(width, height, channel)变为(channel, width, height)
transformer.set_transpose('data', (2,0,1)) 
# 减去均值,注意要先将binaryproto格式均值文件转换为npy格式[此步根据训练model时设置可选]
transformer.set_mean('data', np.load(mean_file_path).mean(1).mean(1))
# 缩放到[0，255]之间
transformer.set_raw_scale('data', 255)
# 交换通道，将图片由RGB变为BGR
transformer.set_channel_swap('data', (2,1,0))
# 加载图片
im=caffe.io.load_image(img)
# 执行上面设置的图片预处理操作，并将图片载入到blob中
net.blobs['data'].data[...] = transformer.preprocess('data',im)

执行测试

#执行测试
out = net.forward()
labels = np.loadtxt(labels_filename, str, delimiter='\t')   #读取类别名称文件
prob= net.blobs['Softmax1'].data[0].flatten() #取出最后一层（Softmax）属于某个类别的概率值，并打印
print prob
order=prob.argsort()[0]  #将概率值排序，取出最大值所在的序号 
print 'the class is:',labels[order]   #将该序号转换成对应的类别名称，并打印
# 取出前五个较大值所在的序号
top_inds = prob.argsort()[::-1][:5]
print 'probabilities and labels:' zip(prob[top_inds], labels[top_inds])

各层信息显示

# params显示：layer名，w，b
for layer_name, param in net.params.items():
    print layer_name + '\t' + str(param[0].data.shape), str(param[1].data.shape)
# blob显示：layer名，输出的blob维度
for layer_name, blob in net.blobs.items():
    print layer_name + '\t' + str(blob.data.shape)

自定义函数:参数/卷积结果可视化

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import caffe
%matplotlib inline
plt.rcParams['figure.figsize'] = (8, 8)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
def show_data(data, padsize=1, padval=0):
"""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)"""
    # data归一化
    data -= data.min()
    data /= data.max()

    # 根据data中图片数量data.shape[0]，计算最后输出时每行每列图片数n
    n = int(np.ceil(np.sqrt(data.shape[0])))
    # padding = ((图片个数维度的padding),(图片高的padding), (图片宽的padding), ....)
    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))

    # 先将padding后的data分成n*n张图像
    data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))
    # 再将（n, W, n, H）变换成(n*w, n*H)
    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
    plt.figure()
    plt.imshow(data,cmap='gray')
    plt.axis('off')
# 示例：显示第一个卷积层的输出数据和权值（filter）
print net.blobs['conv1'].data[0].shape
show_data(net.blobs['conv1'].data[0])
print net.params['conv1'][0].data.shape
show_data(net.params['conv1'][0].data.reshape(32*3,5,5))

自定义：训练过程Loss&Accuracy可视化

import matplotlib.pyplot as plt  
import caffe   
caffe.set_device(0)  
caffe.set_mode_gpu()   
# 使用SGDSolver，即随机梯度下降算法  
solver = caffe.SGDSolver('/home/xxx/mnist/solver.prototxt')  

# 等价于solver文件中的max_iter，即最大解算次数  
niter = 10000 
# 每隔100次收集一次loss数据  
display= 100  

# 每次测试进行100次解算 
test_iter = 100
# 每500次训练进行一次测试
test_interval =500

#初始化 
train_loss = zeros(ceil(niter * 1.0 / display))   
test_loss = zeros(ceil(niter * 1.0 / test_interval))  
test_acc = zeros(ceil(niter * 1.0 / test_interval))  

# 辅助变量  
_train_loss = 0; _test_loss = 0; _accuracy = 0  
# 进行解算  
for it in range(niter):  
    # 进行一次解算  
    solver.step(1)  
    # 统计train loss  
    _train_loss += solver.net.blobs['SoftmaxWithLoss1'].data  
    if it % display == 0:  
        # 计算平均train loss  
        train_loss[it // display] = _train_loss / display  
        _train_loss = 0  

    if it % test_interval == 0:  
        for test_it in range(test_iter):  
            # 进行一次测试  
            solver.test_nets[0].forward()  
            # 计算test loss  
            _test_loss += solver.test_nets[0].blobs['SoftmaxWithLoss1'].data  
            # 计算test accuracy  
            _accuracy += solver.test_nets[0].blobs['Accuracy1'].data  
        # 计算平均test loss  
        test_loss[it / test_interval] = _test_loss / test_iter  
        # 计算平均test accuracy  
        test_acc[it / test_interval] = _accuracy / test_iter  
        _test_loss = 0  
        _accuracy = 0  

# 绘制train loss、test loss和accuracy曲线  
print '\nplot the train loss and test accuracy\n'  
_, ax1 = plt.subplots()  
ax2 = ax1.twinx()  

# train loss -> 绿色  
ax1.plot(display * arange(len(train_loss)), train_loss, 'g')  
# test loss -> 黄色  
ax1.plot(test_interval * arange(len(test_loss)), test_loss, 'y')  
# test accuracy -> 红色  
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')  

ax1.set_xlabel('iteration')  
ax1.set_ylabel('loss')  
ax2.set_ylabel('accuracy')  
plt.show()