如果不需要绘制曲线，只需要训练出一个caffemodel, 直接调用solver.solve()就可以了。如果要绘制曲线，就需要把迭代过程中的值保存下来，因此不能直接调用solver.solve(), 需要迭代。在迭代过程中，每迭代200次测试一次
#加载必要的库
import numpy as np
import matplotlib.pyplot as plt #matplotlib inline
import sys,os,caffe
#设置当前目录
caffe_root = '/caffe/'
sys.path.insert(0, caffe_root + 'python')
os.chdir(caffe_root)
# set the solver prototxt
caffe.set_mode_cpu()
solver = caffe.SGDSolver('examples/cifar10/cifar10_quick_solver.prototxt')
niter = 4000
test_interval = 200
train_loss = np.zeros(niter)
test_acc = np.zeros(int(np.ceil(niter / test_interval)))
# the main solver loop
for it in range(niter):
solver.step(1) # SGD by Caffe
# store the train loss
train_loss[it] = solver.net.blobs['loss'].data
solver.test_nets[0].forward(start='conv1')
if it % test_interval == 0:
acc = solver.test_nets[0].blobs['accuracy'].data
print('Iteration', it, 'testing...', 'accuracy:', acc)
test_acc[it // test_interval] = acc
#绘制train过程中的loss曲线，和测试过程中的accuracy曲线。
print(test_acc)
_, ax1 = plt.subplots()
ax2 = ax1.twinx()
ax1.plot(np.arange(niter), train_loss)
ax2.plot(test_interval * np.arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
plt.show()
结果如下：
Iteration 0 testing... accuracy: 0.10000000149 Iteration 200 testing... accuracy: 0.419999986887 Iteration 400 testing... accuracy: 0.479999989271 Iteration 600 testing... accuracy: 0.540000021458 Iteration 800 testing... accuracy: 0.620000004768 Iteration 1000 testing... accuracy: 0.629999995232 Iteration 1200 testing... accuracy: 0.649999976158 Iteration 1400 testing... accuracy: 0.660000026226 Iteration 1600 testing... accuracy: 0.660000026226 Iteration 1800 testing... accuracy: 0.670000016689 Iteration 2000 testing... accuracy: 0.709999978542 Iteration 2200 testing... accuracy: 0.699999988079 Iteration 2400 testing... accuracy: 0.75 Iteration 2600 testing... accuracy: 0.740000009537 Iteration 2800 testing... accuracy: 0.769999980927 Iteration 3000 testing... accuracy: 0.75 Iteration 3200 testing... accuracy: 0.699999988079 Iteration 3400 testing... accuracy: 0.740000009537 Iteration 3600 testing... accuracy: 0.72000002861 Iteration 3800 testing... accuracy: 0.769999980927 CPU times: user 41.7 s, sys: 54.2 s, total: 1min 35s Wall time: 1min 18s[0.11 0.40000001 0.47999999 0.51999998 0.60000002 0.62
0.67000002 0.60000002 0.69999999 0.69999999 0.68000001 0.73000002
0.69999999 0.75999999 0.72000003 0.69999999 0.70999998 0.69
0.72000003 0.74000001]
参考博文：www.cnblogs.com/denny402/p/5110204.html