caffe Python API 之可视化

一、显示各层

# 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)

二、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))

三、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()