基于pycaffe的网络训练和结果分析（mnist数据集）

  1 import numpy as np
  2 import caffe
  3 from caffe import layers as L, params as P, proto, to_proto
  4 
  5 # file path
  6 root = ‘/home/your-account/DL-Analysis/‘
  7 train_list = root + ‘mnist/mnist_train_lmdb‘
  8 test_list = root + ‘mnist/mnist_test_lmdb‘
  9 
 10 train_proto = root + ‘mnist/LeNet/train.prototxt‘
 11 test_proto = root + ‘mnist/LeNet/test.prototxt‘
 12 
 13 deploy_proto = root + ‘mnist/LeNet/deploy.prototxt‘
 14 
 15 solver_proto = root + ‘mnist/LeNet/solver.prototxt‘
 16 
 17 def LeNet(data_list, batch_size, IncludeAccuracy = False, deploy = False):
 18     """
 19     LeNet define
 20     """
 21 
 22     if not(deploy):
 23         data, label =  L.Data(source = data_list,
 24                               backend = P.Data.LMDB,
 25                               batch_size = batch_size,
 26                               ntop = 2,
 27                               transform_param = dict(scale = 0.00390625))
 28     else:
 29         data = L.Input(input_param = {‘shape‘: {‘dim‘: [64, 1, 28, 28]}})
 30     
 31     conv1 = L.Convolution(data,
 32                           kernel_size = 5,
 33                           stride = 1,
 34                           num_output = 20,
 35                           pad = 0,
 36                           weight_filler = dict(type = ‘xavier‘))
 37     
 38     pool1 = L.Pooling(conv1,
 39                       pool = P.Pooling.MAX,
 40                       kernel_size = 2,
 41                       stride = 2)
 42     
 43     conv2 = L.Convolution(pool1,
 44                           kernel_size = 5,
 45                           stride = 1,
 46                           num_output = 50,
 47                           pad = 0,
 48                           weight_filler = dict(type = ‘xavier‘))
 49     
 50     pool2 = L.Pooling(conv2,
 51                       pool = P.Pooling.MAX,
 52                       kernel_size = 2,
 53                       stride = 2)
 54 
 55     ip1 = L.InnerProduct(pool2,
 56                          num_output = 500,
 57                          weight_filler = dict(type = ‘xavier‘))
 58     
 59     relu1 = L.ReLU(ip1,
 60                    in_place = True)
 61     
 62     ip2 = L.InnerProduct(relu1,
 63                          num_output = 10,
 64                          weight_filler = dict(type = ‘xavier‘))
 65     
 66     #loss = L.SoftmaxWithLoss(ip2, label)
 67 
 68     if ( not(IncludeAccuracy) and not(deploy) ):
 69         # train net
 70         loss = L.SoftmaxWithLoss(ip2, label)
 71         return to_proto(loss)
 72     
 73     elif ( IncludeAccuracy and not(deploy) ):
 74         # test net
 75         loss = L.SoftmaxWithLoss(ip2, label)
 76         Accuracy = L.Accuracy(ip2, label)
 77         return to_proto(loss, Accuracy)
 78     
 79     else:
 80         # deploy net
 81         prob = L.Softmax(ip2)
 82         return to_proto(prob)
 83     
 84 def WriteNet():
 85     """
 86     write proto to file
 87     """
 88     
 89     # train net
 90     with open(train_proto, ‘w‘) as file:
 91         file.write( str(LeNet(train_list, 64, IncludeAccuracy = False, deploy = False)) )
 92 
 93     # test net
 94     with open(test_proto, ‘w‘) as file:
 95         file.write( str(LeNet(test_list, 100, IncludeAccuracy = True, deploy = False)) )
 96 
 97     # deploy net
 98     with open(deploy_proto, ‘w‘) as file:
 99         file.write( str(LeNet(‘not need‘, 64, IncludeAccuracy = False, deploy = True)) )
100 
101 def GenerateSolver(solver_file, train_net, test_net):
102     """
103     generate the solver file
104     """
105     
106     s = proto.caffe_pb2.SolverParameter()
107     s.train_net = train_net
108     s.test_net.append(test_net)
109     s.test_interval = 100
110     s.test_iter.append(100)
111     s.max_iter = 10000
112     s.base_lr = 0.01
113     s.momentum = 0.9
114     s.weight_decay = 5e-4
115     s.lr_policy = ‘step‘
116     s.stepsize = 3000
117     s.gamma = 0.1
118     s.display = 100
119     s.snapshot = 0
120     s.snapshot_prefix = ‘./lenet‘
121     s.type = ‘SGD‘
122     s.solver_mode = proto.caffe_pb2.SolverParameter.GPU
123 
124     with open(solver_file, ‘w‘) as file:
125         file.write( str(s) )
126 
127 def Training(solver_file):
128     """
129     training
130     """
131 
132     caffe.set_device(0)
133     caffe.set_mode_gpu() 
134     solver = caffe.get_solver(solver_file)
135     #solver.solve() # solve completely
136     
137     number_iteration = 10000
138 
139     # collect the information
140     display = 100
141 
142     # test information
143     test_iteration = 100
144     test_interval = 100
145 
146     # loss and accuracy information
147     train_loss = np.zeros( np.ceil(number_iteration * 1.0 / display) )
148     test_loss = np.zeros( np.ceil(number_iteration * 1.0 / test_interval) )
149     test_accuracy = np.zeros( np.ceil(number_iteration * 1.0 / test_interval) )
150 
151     # tmp variables
152     _train_loss = 0; _test_loss = 0; _test_accuracy = 0;
153 
154     # main loop
155     for iter in range(number_iteration):
156         solver.step(1)
157 
158         # save model during training
159         if iter in [10, 30, 60, 100, 300, 600, 1000, 3000, 6000, number_iteration - 1]:
160             string = ‘lenet_iter_%(iter)d.caffemodel‘%{‘iter‘: iter}
161             solver.net.save(string)
162 
163         if 0 == iter % display:
164             train_loss[iter // display] = solver.net.blobs[‘SoftmaxWithLoss1‘].data
165             
166         ‘‘‘
167         # accumulate the train loss
168         _train_loss += solver.net.blobs[‘SoftmaxWithLoss1‘].data
169         if 0 == iter % display:
170             train_loss[iter // display] = _train_loss / display
171             _train_loss = 0
172         ‘‘‘
173 
174         if 0 == iter % test_interval:
175             for test_iter in range(test_iteration):
176                 solver.test_nets[0].forward()
177                 _test_loss += solver.test_nets[0].blobs[‘SoftmaxWithLoss1‘].data
178                 _test_accuracy += solver.test_nets[0].blobs[‘Accuracy1‘].data
179 
180             test_loss[iter / test_interval] = _test_loss / test_iteration
181             test_accuracy[iter / test_interval] = _test_accuracy / test_iteration
182             _test_loss = 0
183             _test_accuracy = 0
184 
185     # save for analysis
186     np.save(‘./train_loss.npy‘, train_loss)
187     np.save(‘./test_loss.npy‘, test_loss)
188     np.save(‘./test_accuracy.npy‘, test_accuracy)
189     
190 if __name__ == ‘__main__‘:
191     WriteNet()
192     GenerateSolver(solver_proto, train_proto, test_proto)
193 Training(solver_proto)